Skip to content

feat(mcp): add opt-in authenticated tool discovery - #7591

Merged
prekshivyas merged 10 commits into
mainfrom
feat/mcp-status-tools-current
Jul 27, 2026
Merged

feat(mcp): add opt-in authenticated tool discovery#7591
prekshivyas merged 10 commits into
mainfrom
feat/mcp-status-tools-current

Conversation

@ericksoa

@ericksoa ericksoa commented Jul 26, 2026

Copy link
Copy Markdown
Contributor

Summary

Adds an opt-in nemoclaw <sandbox> mcp status <server> --tools diagnostic that lists tool names through the configured MCP registration without invoking tools. This is a clean, linear replacement for the accumulated branch in #6904, rebuilt directly on current main around the accepted #6901 trust boundary and current three-adapter architecture.

Related Issue

Closes #6901

Changes

  • Add bounded MCP initialize and paginated tools/list discovery with strict time, request, response, page, tool, cursor, and name limits.
  • Reuse the existing credential provider, network policy, MCP registration, and adapter ancestry; do not add a host fallback or a new policy path.
  • Pin, lock, audit, and bundle one official MCP SDK runtime into the OpenClaw, Hermes, and Deep Agents images.
  • Add status, JSON, help, and user documentation for the opt-in diagnostic.
  • Add unit, image-contract, support, and protected-compatible live E2E coverage for all three adapters, pagination, credential rewriting, session/protocol metadata, best-effort cleanup behavior, and the invariant that discovery never sends tools/call.
  • The shared runtime is required because Hermes and Deep Agents cannot reuse OpenClaw's mcporter; separate adapter clients would duplicate a security-sensitive protocol path. test/e2e/live/mcp-bridge.test.ts and the runtime/image contract tests protect the shared implementation.

Type of Change

  • Code change (feature, bug fix, or refactor)
  • Code change with doc updates
  • Doc only (prose changes, no code sample modifications)
  • Doc only (includes code sample changes)

Quality Gates

  • Tests added or updated for changed behavior
  • Existing tests cover changed behavior — justification:
  • Tests not applicable — justification:
  • Docs updated for user-facing behavior changes
  • Docs not applicable — justification:
  • Sensitive paths changed (security, policy, credentials, preflight, onboarding, inference, runner, sandbox, or messaging)
  • Sensitive-path review completed or maintainer-approved waiver recorded — reviewer/approval link/justification: Codex Desktop reviewed exact head 6688fe6fc3fed997fe89e7322429c1f5505fe5d9 across all nine repository security categories, including independent validation of the fail-closed evidence path, and found no issues. Exact-head advisors, CodeQL, secret scanning, CI, and protected E2E passed. This does not replace the fresh human security approval required before merge. Accepted trust contract: Add opt-in live MCP tool discovery to mcp status #6901 (comment)
  • Non-success, skipped, or missing CI check accepted by maintainer — check name, approval link, and follow-up issue:

Documentation Writer Review

  • Documentation writer subagent reviewed the completed changes
  • Result: docs-updated
  • Evidence: docs/manage-sandboxes/manage-mcp-servers.mdx, docs/reference/commands.mdx, test/e2e/README.md, tools/mcp-tool-discovery-runtime/dependency-review.md; reviewed terminology, structure, voice, security bounds, and code-sample presentation against accepted Add opt-in live MCP tool discovery to mcp status #6901; npm run docs passed with 0 errors.
  • Agent: Codex Desktop

DGX Station Hardware Evidence

  • Tested on DGX Station
  • Tested commit:
  • Station profile/scenario:
  • Result:
  • Supporting evidence:

Verification

  • PR description includes a Signed-off-by: line and every commit appears as Verified in GitHub
  • Normal pre-commit, commit-msg, and pre-push hooks passed, or npm run check:diff passed when hooks were skipped or unavailable
  • Targeted behavior tests pass for the current change set, or tests are marked not applicable above — command/result or justification: CLI-focused tests passed (41); compatibility classifier, real-CLI, risk reporter, base-gate, and workflow/uploader suites passed (81); the four unrelated support files that timed out only under whole-project local contention passed 101/101 on isolated rerun. E2E semantic phase coverage passed (125 tests across 82 files); shared fake-server integration passed (10/10). npm run typecheck:cli, npm run check:diff, runtime/project boundary checks, and npm run docs passed on exact head 6688fe6fc3fed997fe89e7322429c1f5505fe5d9.
  • Applicable broad gate passed — npm test for broad runtime/test-harness changes; npm run check for repo-wide validation/coverage changes — command/result: Exact-head PR CI passed static checks, build/typecheck, reviewed npm audit, installer integration, plugin tests, and all 8 CLI shards (https://github.com/NVIDIA/NemoClaw/actions/runs/30213491792); self-hosted CI passed both sandbox-image builds and all smoke/integration jobs (https://github.com/NVIDIA/NemoClaw/actions/runs/30213492138); protected E2E passed all 14 selected concrete jobs and controller evidence verification (https://github.com/NVIDIA/NemoClaw/actions/runs/30213967327; https://github.com/NVIDIA/NemoClaw/actions/runs/30213947255).
  • Quality Gates section completed with required justifications or waivers
  • No secrets, API keys, or credentials committed
  • npm run docs builds without warnings (doc changes only) — 0 errors; two pre-existing Fern warnings remain.
  • Doc pages follow the style guide (doc changes only)
  • New doc pages include SPDX header and frontmatter (new pages only)

Signed-off-by: Aaron Erickson aerickson@nvidia.com

Summary by CodeRabbit

  • New Features
    • Added mcp status --tools to retrieve a point-in-time list of a server’s advertised MCP tool names, with bounded results and truncation when limits are reached.
    • mcp status JSON now includes toolDiscovery (ok, count, tools, truncated, optional detail); --tools can run alongside --probe/--no-probe with consistent redaction.
  • Documentation
    • Updated command reference and MCP server management docs to explain discovery behavior, readiness/trust requirements, output structure, and rebuild notes for older images.
  • Bug Fixes / Security
    • Improved discovery validation and tightened failure handling to avoid malformed/unsafe inventories and reduce risk of sensitive data leakage.

ericksoa added 3 commits July 26, 2026 06:56
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Copilot AI review requested due to automatic review settings July 26, 2026 14:51
@ericksoa ericksoa added area: cli Command line interface, flags, terminal UX, or output area: integrations Third-party service integration behavior feature PR adds or expands user-visible functionality v0.0.97 labels Jul 26, 2026
@ericksoa ericksoa self-assigned this Jul 26, 2026

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

@coderabbitai

coderabbitai Bot commented Jul 26, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

Note

Reviews paused

It looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the reviews.auto_review.auto_pause_after_reviewed_commits setting.

Use the following commands to manage reviews:

  • @coderabbitai resume to resume automatic reviews.
  • @coderabbitai review to trigger a single review.

Use the checkboxes below for quick actions:

  • ▶️ Resume reviews
  • 🔍 Trigger review
📝 Walkthrough

Walkthrough

Adds opt-in mcp status --tools discovery through a shared, bounded MCP runtime. The change covers adapter integration, authenticated pagination, result validation, image packaging, documentation, unit tests, live E2E coverage, and centralized risk-signal evidence.

Changes

MCP tool discovery

Layer / File(s) Summary
Shared discovery runtime
tools/mcp-tool-discovery-runtime/*
Adds the Node MCP client, pagination, cleanup, bounded HTTP handling, dependency review, bundling, and license artifacts.
MCP status integration
src/lib/actions/sandbox/mcp-bridge-*, src/lib/cli/*, docs/...
Adds --tools, readiness gating, sanitized adapter commands, structured results, rendering, and documentation.
Image packaging and staging
Dockerfile, agents/*/Dockerfile, src/lib/sandbox/build-context.ts, scripts/*
Builds, copies, validates, and permission-checks the shared runtime in supported images and build contexts.
Unit validation
src/lib/actions/sandbox/*.test.ts, test/*
Covers argument validation, pagination, limits, redaction, readiness, CLI behavior, image contracts, and staging.
Live E2E validation
test/e2e/live/*, tools/e2e/live-vitest-invocation.mts
Verifies authenticated MCP initialization, paginated tools/list, session cleanup, selector routing, and no tools/call across agents.
Risk-signal evidence
tools/e2e/risk-signal.ts, tools/e2e/mcp-bridge-runtime-compatibility.mts, test/e2e/...
Centralizes risk-signal construction and validates conditional artifact generation for compatibility evidence.

Estimated code review effort: 5 (Critical) | ~120 minutes

Sequence Diagram(s)

sequenceDiagram
  participant CLI
  participant MCPBridgeStatus
  participant SandboxRuntime
  participant ManagedMCPServer
  CLI->>MCPBridgeStatus: mcp status server --tools
  MCPBridgeStatus->>SandboxRuntime: execute shared discovery runtime
  SandboxRuntime->>ManagedMCPServer: initialize and tools/list
  ManagedMCPServer-->>SandboxRuntime: paginated tool names
  SandboxRuntime-->>MCPBridgeStatus: bounded discovery result
  MCPBridgeStatus-->>CLI: render toolDiscovery status
Loading

Possibly related PRs

Suggested labels: area: e2e, area: docs, platform: container

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Docstring Coverage ⚠️ Warning Docstring coverage is 1.89% which is insufficient. The required threshold is 80.00%. Write docstrings for the functions missing them to satisfy the coverage threshold.
✅ Passed checks (4 passed)
Check name Status Explanation
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly matches the main change: an opt-in authenticated MCP tool discovery feature.
✨ Finishing Touches
📝 Generate docstrings
  • Create stacked PR
  • Commit on current branch
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch feat/mcp-status-tools-current

Comment @coderabbitai help to get the list of available commands.

@github-code-quality

github-code-quality Bot commented Jul 26, 2026

Copy link
Copy Markdown
Contributor

Code Coverage Overview

Languages: TypeScript

TypeScript / code-coverage/plugin

The overall coverage in commit 7a0a432 in the feat/mcp-status-tool... branch remains at 96%, unchanged from commit a02a3b9 in the main branch.

TypeScript / code-coverage/cli

The overall coverage in commit 7a0a432 in the feat/mcp-status-tool... branch is 80%. The coverage in commit a02a3b9 in the main branch is 81%.

Show a code coverage summary of the most impacted files.
File main a02a3b9 feat/mcp-status-tool... 7a0a432 +/-
src/lib/onboard...ndbox-create.ts 83% 33% -50%
src/lib/actions...-add-restart.ts 19% 10% -9%
src/lib/actions...x/mcp-bridge.ts 43% 35% -8%
src/lib/onboard...ndbox-create.ts 91% 83% -8%
src/lib/actions...lution-probe.ts 93% 88% -5%
src/lib/actions...e-validation.ts 84% 81% -3%
src/lib/onboard...eway-service.ts 82% 81% -1%
src/lib/shields/index.ts 71% 72% +1%
src/lib/actions...ol-discovery.ts 0% 82% +82%
src/lib/actions...time-command.ts 0% 82% +82%

Updated July 27, 2026 01:39 UTC

@github-actions

Copy link
Copy Markdown
Contributor

@github-actions

github-actions Bot commented Jul 26, 2026

Copy link
Copy Markdown
Contributor

PR Review Advisor — No blocking findings reported

Advisor assessment: No blocking advisor findings reported
Next action: No advisor follow-up needed.
Findings: 0 blockers · 0 warnings · 0 suggestions

Model lanes

  • GPT-5.6 Terra (primary): Completed · medium confidence · 0 blockers · 0 warnings · 0 suggestions
  • Nemotron 3 Ultra (second opinion): Completed · high confidence · 0 blockers · 0 warnings · 0 suggestions
  • Model comparison: normalized findings match; normalized E2E selections differ; severity counts match.

Nemotron output stays in workflow artifacts and does not change the assessment above.

E2E guidance

Advisory only. E2E / PR Gate selects and runs jobs independently.

Recommended E2E: cloud-onboard, credential-sanitization, full-e2e, hermes-e2e, security-posture, mcp-bridge, mcp-bridge-dev, onboard-repair, onboard-resume, ubuntu-repo-cloud-langchain-deepagents-code

2 optional E2E recommendations
  • ubuntu-repo-cloud-openclaw
  • docs-validation

Workflow run details

This automated review informs maintainers. Warnings and suggestions do not require a response. A maintainer decides whether to merge.

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🧹 Nitpick comments (2)
tools/mcp-tool-discovery-runtime/install-reviewed-runtime.sh (1)

19-28: 🔒 Security & Privacy | 🔵 Trivial | 💤 Low value

Use mktemp instead of a fixed /tmp path for the decoded CA.

$decoded uses a predictable, fixed filename. Using mktemp avoids a symlink/TOCTOU race on a shared /tmp during the build stage.

🔒 Suggested fix
-  decoded=/tmp/nemoclaw-mcp-runtime-ca.decoded
+  decoded=$(mktemp)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@tools/mcp-tool-discovery-runtime/install-reviewed-runtime.sh` around lines 19
- 28, Replace the fixed /tmp path assigned to decoded in
install-reviewed-runtime.sh with a securely created temporary file using mktemp,
while preserving the existing base64 decode, awk extraction, and cleanup flow.
test/mcp-tool-discovery-image-contract.test.ts (1)

16-27: 🎯 Functional Correctness | 🔵 Trivial | 🏗️ Heavy lift

Assert the assembled-image contract, not Dockerfile text.

These assertions lock in exact instructions but do not prove the runtime is present or executable in an image. Exercise the built image and verify the canonical module emits the expected contract instead.

As per path instructions, “Prefer observable outcomes through the public boundary over source-text, private-shape, or mock-call assertions.”

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@test/mcp-tool-discovery-image-contract.test.ts` around lines 16 - 27, Replace
the Dockerfile text assertions in the “MCP tool discovery image contract” test
with an assembled-image integration check. Build or load each image represented
by dockerfiles, execute the canonical mcp-tool-discovery module at runtimeRoot,
and assert that it is present, executable, and emits the expected tool-discovery
contract; avoid validating COPY or command strings directly.

Source: Path instructions

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Nitpick comments:
In `@test/mcp-tool-discovery-image-contract.test.ts`:
- Around line 16-27: Replace the Dockerfile text assertions in the “MCP tool
discovery image contract” test with an assembled-image integration check. Build
or load each image represented by dockerfiles, execute the canonical
mcp-tool-discovery module at runtimeRoot, and assert that it is present,
executable, and emits the expected tool-discovery contract; avoid validating
COPY or command strings directly.

In `@tools/mcp-tool-discovery-runtime/install-reviewed-runtime.sh`:
- Around line 19-28: Replace the fixed /tmp path assigned to decoded in
install-reviewed-runtime.sh with a securely created temporary file using mktemp,
while preserving the existing base64 decode, awk extraction, and cleanup flow.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: b5ec1e15-6793-4312-ad0c-217fc6312441

📥 Commits

Reviewing files that changed from the base of the PR and between d4a859a and 7f69730.

⛔ Files ignored due to path filters (1)
  • tools/mcp-tool-discovery-runtime/package-lock.json is excluded by !**/package-lock.json
📒 Files selected for processing (37)
  • Dockerfile
  • agents/hermes/Dockerfile
  • agents/langchain-deepagents-code/Dockerfile
  • docs/manage-sandboxes/manage-mcp-servers.mdx
  • docs/reference/commands.mdx
  • scripts/check-dcode-profile-import-gate.sh
  • src/lib/actions/sandbox/mcp-bridge-contracts.ts
  • src/lib/actions/sandbox/mcp-bridge-render.ts
  • src/lib/actions/sandbox/mcp-bridge-resolution-probe-security.test.ts
  • src/lib/actions/sandbox/mcp-bridge-resolution-probe.ts
  • src/lib/actions/sandbox/mcp-bridge-runtime-command.ts
  • src/lib/actions/sandbox/mcp-bridge-status-resolution.test.ts
  • src/lib/actions/sandbox/mcp-bridge-status.ts
  • src/lib/actions/sandbox/mcp-bridge-tool-discovery.test.ts
  • src/lib/actions/sandbox/mcp-bridge-tool-discovery.ts
  • src/lib/actions/sandbox/mcp-bridge.ts
  • src/lib/actions/sandbox/mcp-tool-discovery-runtime.test.ts
  • src/lib/cli/public-display-mcp.test.ts
  • src/lib/cli/public-display-mcp.ts
  • src/lib/sandbox/build-context.ts
  • test/e2e/live/mcp-bridge-servers.ts
  • test/e2e/live/mcp-bridge-tool-discovery.ts
  • test/e2e/live/mcp-bridge.test.ts
  • test/e2e/support/live-vitest-invocation.test.ts
  • test/langchain-deepagents-code-profile-build-gate.test.ts
  • test/mcp-tool-discovery-image-contract.test.ts
  • test/openclaw-final-image-layout.test.ts
  • test/sandbox-build-context.test.ts
  • tools/e2e/live-vitest-invocation.mts
  • tools/mcp-tool-discovery-runtime/build-runtime.ts
  • tools/mcp-tool-discovery-runtime/dependency-review.md
  • tools/mcp-tool-discovery-runtime/install-reviewed-runtime.sh
  • tools/mcp-tool-discovery-runtime/mcp-tool-discovery.ts
  • tools/mcp-tool-discovery-runtime/package.json
  • tools/mcp-tool-discovery-runtime/tool-discovery-core.ts
  • tools/mcp-tool-discovery-runtime/tsconfig.json
  • tsconfig.cli.json

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Copilot AI review requested due to automatic review settings July 26, 2026 15:26

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Copilot AI review requested due to automatic review settings July 26, 2026 16:35

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

@ericksoa ericksoa added area: sandbox OpenShell sandbox lifecycle, runtime, config, or recovery area: security Security controls, permissions, secrets, or hardening integration: openclaw OpenClaw integration behavior integration: hermes Hermes integration behavior integration: dcode LangChain Deep Code integration behavior security labels Jul 26, 2026
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Copilot AI review requested due to automatic review settings July 26, 2026 17:52

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

Copilot AI review requested due to automatic review settings July 26, 2026 19:01
@copy-pr-bot

copy-pr-bot Bot commented Jul 26, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

Copilot AI review requested due to automatic review settings July 27, 2026 00:06

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review is ineligible. To be eligible to request a review, you need a paid Copilot license, or your organization must enable Copilot code review.

ericksoa added 2 commits July 26, 2026 17:52
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Copilot AI review requested due to automatic review settings July 27, 2026 01:30

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

@ericksoa ericksoa added the needs: review PR is conflict-free and awaiting maintainer review label Jul 27, 2026

@prekshivyas prekshivyas left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Reviewed exact head 7a0a432. Accepted #6901 scope, full MCP runtime/dependency and nine-category security review, exact documentation receipt, contributor compliance, current-base mergeability, and all 49 current CI/E2E checks pass.

@prekshivyas
prekshivyas merged commit fdf14f5 into main Jul 27, 2026
72 of 74 checks passed
@prekshivyas
prekshivyas deleted the feat/mcp-status-tools-current branch July 27, 2026 02:11
@prekshivyas prekshivyas mentioned this pull request Jul 27, 2026
23 tasks
apurvvkumaria pushed a commit that referenced this pull request Jul 27, 2026
<!-- markdownlint-disable MD041 -->
## Summary

Add the canonical `docs/changelog/2026-07-25.mdx` release entry with the
exact `## v0.0.96` heading.
The entry reconciles all 90 first-parent commits since v0.0.95 with all
92 merged PRs in the live `v0.0.96` label ledger and groups the
user-visible changes by operator journey.

## Changes

- Add the parser-safe dated MDX changelog entry for v0.0.96 with
root-absolute links to the focused user guides.
- Source summary:
- [#7194](#7194) ->
`docs/changelog/2026-07-25.mdx`: Document persistent baseline network
policy exclusions and their inspection, rebuild, and snapshot behavior.
- [#7188](#7188),
[#7427](#7427), and
[#7546](#7546) ->
`docs/changelog/2026-07-25.mdx`: Document DNS-backed HTTPS inference
routing, keyless loopback endpoints, and provider-marker isolation.
- [#7238](#7238) ->
`docs/changelog/2026-07-25.mdx`: Document blueprint sandbox and provider
identifier validation before state writes or OpenShell calls, with
bounded terminal-safe rejection previews.
- [#7319](#7319),
[#7274](#7274),
[#7528](#7528),
[#7353](#7353), and
[#7560](#7560) ->
`docs/changelog/2026-07-25.mdx`: Document the managed default gateway
service, onboarding readiness, and container-runtime identity
safeguards.
- [#7349](#7349),
[#7498](#7498),
[#7406](#7406),
[#7196](#7196),
[#7559](#7559),
[#7421](#7421),
[#7510](#7510),
[#7295](#7295), and
[#7565](#7565) ->
`docs/changelog/2026-07-25.mdx`: Document gateway-scoped status,
lifecycle diagnostics, managed MCP recovery, delete-edge safeguards, and
fail-closed CLI prompt and command output.
- [#7591](#7591) ->
`docs/changelog/2026-07-25.mdx`: Document opt-in authenticated MCP
tool-name discovery, its bounded and names-only contract, probe
interaction, and rebuild requirement.
- [#7305](#7305),
[#7480](#7480),
[#7471](#7471),
[#7365](#7365), and
[#7541](#7541) ->
`docs/changelog/2026-07-25.mdx`: Document installer version checks,
version-tag reporting, license guidance, WSL Ollama selection, and DGX
Station vLLM detection.
- [#7482](#7482),
[#7466](#7466),
[#7208](#7208),
[#7434](#7434), and
[#7586](#7586) ->
`docs/changelog/2026-07-25.mdx`: Document Ollama resource details,
reasoning precedence, Hermes onboarding behavior, and preserved managed
Hermes BuildKit failures.

- [#6830](#6830),
[#7492](#7492),
[#7563](#7563), and
[#7582](#7582) ->
`docs/changelog/2026-07-25.mdx`: Document the authoritative OpenClaw
production lock, fixed managed-image dependencies, immutable Hermes base
adoption, and Hermes image-size reduction.
- [#7505](#7505),
[#7530](#7530),
[#7547](#7547),
[#7508](#7508),
[#7548](#7548),
[#7549](#7549),
[#7537](#7537),
[#7534](#7534),
[#7515](#7515),
[#7511](#7511),
[#7551](#7551),
[#7562](#7562),
[#7575](#7575),
[#7496](#7496),
[#7594](#7594),
[#7595](#7595), and
[#7599](#7599) ->
`docs/changelog/2026-07-25.mdx`: Summarize release validation, transient
and bounded dispatch reconciliation, exact pre-tag qualification,
identity revalidation, npm-audit retry, sharding, image reuse, timeout,
telemetry, and workflow-hardening changes.
- Reconciled without separate changelog prose:
- [#7539](#7539),
[#7526](#7526),
[#7507](#7507),
[#7506](#7506),
[#7519](#7519),
[#7516](#7516),
[#7396](#7396),
[#7254](#7254),
[#7583](#7583),
[#7596](#7596), and
[#7598](#7598): Test-harness or
fixture-only changes.
- [#7403](#7403),
[#7161](#7161),
[#6877](#6877),
[#7531](#7531),
[#7525](#7525),
[#7522](#7522),
[#7536](#7536),
[#7552](#7552),
[#7566](#7566),
[#7553](#7553),
[#7561](#7561),
[#7577](#7577),
[#7569](#7569),
[#7585](#7585),
[#7584](#7584),
[#7592](#7592),
[#7580](#7580),
[#7571](#7571),
[#7517](#7517),
[#7589](#7589),
[#7402](#7402),
[#7558](#7558),
[#7544](#7544), and
[#7601](#7601): Dependency,
internal recovery, validation, contributor-workflow, E2E optimization,
telemetry, or CI trust changes with no separate user-facing release
claim.
- [#7556](#7556),
[#7573](#7573),
[#7576](#7576), and
[#7578](#7578): Experimental
repository-maintainer conflict automation with no canonical user
documentation surface.

## Type of Change

- [ ] Code change (feature, bug fix, or refactor)
- [ ] Code change with doc updates
- [x] Doc only (prose changes, no code sample modifications)
- [ ] Doc only (includes code sample changes)

## Quality Gates

- [ ] Tests added or updated for changed behavior
- [x] Existing tests cover changed behavior — justification:
`test/changelog-docs.test.ts` validates dated changelog structure,
version headings, and published links.
- [ ] Tests not applicable — justification:
- [x] Docs updated for user-facing behavior changes
- [ ] Docs not applicable — justification:
- [ ] Sensitive paths changed (security, policy, credentials, preflight,
onboarding, inference, runner, sandbox, or messaging)
- [ ] Sensitive-path review completed or maintainer-approved waiver
recorded — reviewer/approval link/justification:
- [ ] Non-success, skipped, or missing CI check accepted by maintainer —
check name, approval link, and follow-up issue:

## Documentation Writer Review

- [x] Documentation writer subagent reviewed the completed changes
- Result: `docs-updated`
- Evidence: Reviewed `docs/changelog/2026-07-25.mdx` at exact head
`0f5dedb47` against 90 first-parent release commits and 92 merged PRs
labeled `v0.0.96`. Verified parser-safe MDX SPDX, the exact version
heading, literal CLI names, writing style, skip terms, all 20
root-absolute published links, and the accepted #7591 opt-in
authenticated discovery bounds. #7544, #7599, and #7601 remain internal
or CI-only release-ledger entries. Changelog tests passed 6/6, the docs
build passed with 0 errors and two pre-existing Fern warnings, and `npm
run check:diff` plus the final diff check passed.
- Agent: Codex Desktop documentation-writer subagent
<!-- docs-review-head-sha: 0f5dedb -->
<!-- docs-review-agents-blob-sha: be20a09 -->

## DGX Station Hardware Evidence

- [ ] Tested on DGX Station
- Tested commit:
- Station profile/scenario:
- Result:
- Supporting evidence:

## Verification

- [x] PR description includes a `Signed-off-by:` line and every commit
appears as `Verified` in GitHub
- [x] Normal `pre-commit`, `commit-msg`, and `pre-push` hooks passed, or
`npm run check:diff` passed when hooks were skipped or unavailable
- [x] Targeted behavior tests pass for the current change set, or tests
are marked not applicable above — `npx vitest run
test/changelog-docs.test.ts`: 6/6 passed.
- [ ] Applicable broad gate passed — `npm test` for broad
runtime/test-harness changes; `npm run check` for repo-wide
validation/coverage changes — command/result: Not applicable to this
prose-only changelog entry.
- [x] Quality Gates section completed with required justifications or
waivers
- [x] No secrets, API keys, or credentials committed
- [ ] `npm run docs` builds without warnings (doc changes only) — the
build passed with 0 errors and 2 existing Fern warnings; the
published-route check passed.
- [x] Doc pages follow the [style
guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md)
(doc changes only)
- [ ] New doc pages include SPDX header and frontmatter (new pages only)
— native changelog files use the required parser-safe MDX SPDX comment
and no frontmatter.

---
Signed-off-by: Carlos Villela <cvillela@nvidia.com>


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
* Persistent network policy exclusions with consistent restore/exclusion
reporting across rebuilds/snapshots.
* Opt-in MCP tool discovery via `mcp status --tools` with bounded,
redacted authenticated traffic.
* Improved HTTPS inference switching for custom endpoints and refreshed
onboarding/model menu details.
* Refined OpenShell gateway defaults for port `8080`, including more
reliable readiness checks.
* **Bug Fixes**
* Prevent incorrect provider/model restoration after compatible-provider
update failures.
* Preserve managed MCP state after exec loss and tighten gateway/doctor
status scoping.
* **Tests**
* Stronger, fail-closed release validation with hardened
evidence/artifact handoff and bounded timeouts/retries.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Prekshi Vyas <prekshiv@nvidia.com>
Co-authored-by: Prekshi Vyas <prekshiv@nvidia.com>
@cjagwani cjagwani added v0.0.98 and removed v0.0.97 labels Jul 28, 2026
apurvvkumaria pushed a commit that referenced this pull request Jul 28, 2026
<!-- markdownlint-disable MD041 -->
## Summary

Fix managed MCP tool discovery when a compliant Streamable HTTP server
returns an SSE response media type with case variation or parameters.
Upgrade the official MCP SDK to its parsed media-type implementation and
make the regression session part of every reviewed runtime image build.

This replaces #7748 with the same patch on current `main`; the published
branch could not be rebased because repository rules forbid
force-pushes.

## Related Issue

Fixes #7726

## Changes

- Pin `@modelcontextprotocol/sdk` to `1.30.0`, refresh the exact lock,
and record the adjacent-release, provenance, vulnerability, bundle, and
license review.
- Add a real `initialize` → `notifications/initialized` → `tools/list` →
session cleanup fixture using `Text/Event-Stream; Charset=UTF-8`.
- Stage and run that fixture in the shared reviewed runtime installer
used by all agent image builds.

This restores the generic Streamable HTTP/SSE contract accepted in #6901
and implemented in #7591. It does not add a provider-specific
integration or compatibility layer.

## Type of Change

- [x] Code change (feature, bug fix, or refactor)
- [ ] Code change with doc updates
- [ ] Doc only (prose changes, no code sample modifications)
- [ ] Doc only (includes code sample changes)

## Quality Gates

- [x] Tests added or updated for changed behavior
- [ ] Existing tests cover changed behavior — justification:
- [ ] Tests not applicable — justification:
- [ ] Docs updated for user-facing behavior changes
- [x] Docs not applicable — justification: This restores the existing
documented Streamable HTTP discovery lifecycle without changing
commands, flags, configuration, schemas, or supported integrations.
- [x] Sensitive paths changed (security, policy, credentials, preflight,
onboarding, inference, runner, sandbox, or messaging)
- [x] Sensitive-path review completed or maintainer-approved waiver
recorded — reviewer/approval link/justification: Codex security review
passed all nine repository categories; the credential placeholder,
authorization, SSRF, policy, and final-image boundaries are unchanged,
and the exact dependency pin is signature-, attestation-, license-, and
audit-verified.
- [ ] Non-success, skipped, or missing CI check accepted by maintainer —
check name, approval link, and follow-up issue:

## Documentation Writer Review

- [x] Documentation writer subagent reviewed the completed changes
- Result: `no-docs-needed`
- Evidence: Existing docs already describe Streamable HTTP discovery
generically. This restores standards-compliant handling of a valid
response media type and changes no command, flag, configuration,
workflow, supported protocol, or documented user contract. Changelog
work remains part of separate pre-tag release preparation.
- Agent: Codex Desktop `/root/replacement_docs_review`
<!-- docs-review-head-sha: 646d377 -->
<!-- docs-review-agents-blob-sha: be20a09 -->

## DGX Station Hardware Evidence

- [ ] Tested on DGX Station
- Tested commit:
- Station profile/scenario:
- Result:
- Supporting evidence:

## Verification

- [x] PR description includes a `Signed-off-by:` line and every commit
appears as `Verified` in GitHub
- [x] Normal `pre-commit`, `commit-msg`, and `pre-push` hooks passed, or
`npm run check:diff` passed when hooks were skipped or unavailable
- [x] Targeted behavior tests pass for the current change set, or tests
are marked not applicable above — reviewed-runtime session test (1
passed), CLI runtime tests (12 passed), build-context/image-contract
tests (15 passed), runtime and CLI typechecks, bundle allowlist/license
generation, zero-vulnerability production audit, 98 verified registry
signatures, and 11 verified attestations.
- [ ] Applicable broad gate passed — `npm test` for broad
runtime/test-harness changes; `npm run check` for repo-wide
validation/coverage changes — command/result:
- [x] Quality Gates section completed with required justifications or
waivers
- [x] No secrets, API keys, or credentials committed
- [ ] `npm run docs` builds without warnings (doc changes only)
- [ ] Doc pages follow the [style
guide](https://github.com/NVIDIA/NemoClaw/blob/main/docs/CONTRIBUTING.md)
(doc changes only)
- [ ] New doc pages include SPDX header and frontmatter (new pages only)

---
Signed-off-by: Charan Jagwani <cjagwani@nvidia.com>


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

* **New Features**
* Improved MCP tool discovery compatibility with case-variant SSE
response media types.
* Preserved session and protocol headers during tool discovery requests.

* **Bug Fixes**
* Updated the MCP runtime to ensure supported bundled content is
included correctly.

* **Tests**
* Added coverage for SSE discovery, authentication, session cleanup, and
request headers.
* Runtime installation now runs its test suite as part of verification.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Charan Jagwani <cjagwani@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area: cli Command line interface, flags, terminal UX, or output area: integrations Third-party service integration behavior area: sandbox OpenShell sandbox lifecycle, runtime, config, or recovery area: security Security controls, permissions, secrets, or hardening feature PR adds or expands user-visible functionality integration: dcode LangChain Deep Code integration behavior integration: hermes Hermes integration behavior integration: openclaw OpenClaw integration behavior needs: review PR is conflict-free and awaiting maintainer review security

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add opt-in live MCP tool discovery to mcp status

4 participants