Skip to content

docs(rfc): propose the MCP Connections Center stages after the Test button - #39645

Open
RohanK6 wants to merge 1 commit into
mainfrom
crew/conductor/rfc-mcp-connections-center
Open

RohanK6 wants to merge 1 commit into
mainfrom
crew/conductor/rfc-mcp-connections-center

Conversation

@RohanK6

@RohanK6 RohanK6 commented Nov 19, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Propose, as a draft RFC, the three MCP Connections Center stages that follow the per-row Test button, so a maintainer can decide them before any code is written.

Stage 1, the per-row Test button on Customize → MCP Servers, shipped in #38055. On #38054 a maintainer asked for a request-for-change before the remaining stages are built. Stage 2 writes a secret from the browser and would let one probe resolve a secret:// value, which moves a trust boundary.

Why it matters

A person adding an MCP server still edits a config file to set its key, and the Test button cannot check a server whose key is in the vault. Writing the design down first lets a maintainer accept, change or drop the boundary move before it is built.

Not a goal

  • Building any stage. This PR changes no code.
  • A new secret store or a new secret-writing route.
  • A remote MCP catalog or ratings.

What changed (motivation → approach → change)

Symptom: the stages after the Test button have no agreed design, and one of them moves a trust boundary. Cause: #38054 holds them as a request with no RFC. Change: adds docs/request-for-change/rfc-mcp-connections-center.md (status draft) and its index row in docs/request-for-change/README.md. Every claim about today's code was checked at 3cc96a36de. Stage 3 reuses the last error the quarantine store already saves (record_verdicts in src/kiro_crew/mcp_quarantine.py); it adds no second copy.

Backwards compatibility

Compatible: documentation only. No code, config, route or stored value changes.

Removes nothing: no route, field or value is taken away.

Tests

No code changes. scripts/docs-lint.sh passes, and test/test_pr_quality_gates.py and test/test_frontmatter.py pass (358 tests).

Manual verification

N/A — documentation only: the change is a design document and an index row.

Real-machine verification

N/A -- the diff runs nothing: it adds one Markdown design document and one index row.

Screenshots / video

N/A — no UI change.

Related Issues

Part of #38054

Sibling sweep

Swept: ls docs/request-for-change | grep -i mcp and open docs(rfc) pull requests.
Sibling: docs/request-for-change/rfc-connections-mcp-layout.md -- not affected -- it records where MCP Servers lives, not credentials or errors
Sibling: docs/request-for-change/rfc-owner-written-mcp-auto-approve.md -- not affected -- it covers tool approvals, not server keys
Sibling: #33754, #24872, #21975 (open MCP RFC pull requests) -- not affected -- none covers server credentials, last errors or the featured list

Pattern harvest

Rule candidate: none.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title (feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...)
  • Existing tests pass and new tests added for new functionality
  • Self-review completed; code follows project style guidelines
  • Documentation updated (if applicable)
  • No secrets, credentials, or internal references in the diff

Contribution License Agreement

Contributed under the project's Apache-2.0 license.

@RohanK6
RohanK6 requested review from a team and KiroCrewCaptain as code owners November 19, 2026 22:23
@RohanK6
RohanK6 requested a review from iamwhatever November 19, 2026 22:23
@RohanK6
RohanK6 enabled auto-merge (squash) November 19, 2026 22:24
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 19, 2026
@github-actions

github-actions Bot commented Nov 19, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ⏭️ skipped

Revision 9198c0e51adf38b993b341ae30fd921051fc6f48 ships no reviewable capability (docs, tests or generated files only), so there is nothing to inventory. Does not block merge.

@github-actions

github-actions Bot commented Nov 19, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 9198c0e51adf38b993b341ae30fd921051fc6f48 touches no user-facing surface (no changes under website/ or committed screenshots), so the UX review was skipped. Does not block merge.

@github-actions

github-actions Bot commented Nov 19, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS

Design-level review of 9198c0e51adf38b993b341ae30fd921051fc6f48 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

Nothing blocks: this PR only adds a draft RFC and its index row, and it changes no code. It names the one boundary move (Stage 2b) and holds it on Q1.

Notes

  • §5.2 says that once stage 3 lands, "a row that is healthy now can still say when and how it last failed, until an ok clears the record." A row usually becomes healthy because a probe returned ok, and that clears the record, so in practice this rarely happens. Settle Q2 before stage 3 is built, or reword §5.2 so it doesn't promise it.
  • Stage 2a makes two separate calls, POST /api/secrets and then PUT /api/mcp/servers/{name}. The RFC doesn't say what happens if the second call fails: the vault keeps a secret that nothing references, and the server's env is never set. Add one line on whether the form retries the PUT, or rolls back or reuses the vault entry.

[DESIGN-REVIEWED] 9198c0e

Description read

[DESCRIPTION-READ] fbb5184033beadf684a5f5239fd8569a3cf21bf54391f0d3a09bc67f8d4876ac

That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with .github/scripts/pr-description-capture.sh over the same inputs; if it differs, the description or that evidence changed after this verdict was formed and any finding drawn from either is unproven.

@github-actions

github-actions Bot commented Nov 19, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 9198c0e51adf38b993b341ae30fd921051fc6f48 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 9198c0e

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 9198c0e51adf38b993b341ae30fd921051fc6f48 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 19, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 9198c0e51adf38b993b341ae30fd921051fc6f48 — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 9198c0e

Verdict parsed from the review's SHA-scoped output markers for commit 9198c0e51adf38b993b341ae30fd921051fc6f48.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 9198c0e51adf38b993b341ae30fd921051fc6f48 false-positive: <reason, 20 to 500 characters>

@github-actions github-actions Bot added the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Nov 19, 2026
@RohanK6
RohanK6 force-pushed the crew/conductor/rfc-mcp-connections-center branch from c325aa3 to 4edd338 Compare November 19, 2026 23:19
@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision merge conflict Branch has merge conflicts with its base — author must resolve before merge and removed merge conflict Branch has merge conflicts with its base — author must resolve before merge readiness: checking Automated validation is still running labels Nov 19, 2026
@KiroCrewCaptain

KiroCrewCaptain commented Nov 20, 2026 •

Copy link
Copy Markdown
Collaborator

Code change approver recommendation: A person should decide

Why: the decider estimates a 12% chance that this change introduces a defect, within the 12% limit for approving on its own, but it is held at tier 2: design-doc-gate: D.

Docs-only draft RFC plus one index row; it changes no code. Its claims about today's code check out: probe_server refuses secret:// env, record_verdicts saves the last error and ok clears it, _annotate_quarantine copies only probeFailures and probeFailing, both write routes are owner-gated for browser callers, and the featured list is bundled with no order. The one trust-boundary move (stage 2b) is named and blocked on open question Q1, and stage 2a ships without it if the answer is no. Design gaps (stage 2b reading keys for servers someone else registered, vault-name collisions, nothing recorded when quarantine is off) are for the maintainer to settle before implementation and do not make this draft unsound to merge.

Tier: 2, held for a person: design-doc-gate: D.

An automated recommendation, not a review: a maintainer still decides. It approves on its own only when the estimated chance of a defect is at most 12% and the change has at most 400 changed lines. Decider v3c (217fe607) · commit 9198c0e51a · 192 changed lines. If this recommendation is wrong, reply here: replies are how the approver is evaluated.

@RohanK6
RohanK6 force-pushed the crew/conductor/rfc-mcp-connections-center branch from 4edd338 to 086744e Compare November 20, 2026 01:19
@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: passed Eligible automated validation passed for the current revision and removed readiness: passed Eligible automated validation passed for the current revision merge conflict Branch has merge conflicts with its base — author must resolve before merge readiness: checking Automated validation is still running labels Nov 20, 2026
@KiroCrewCaptain

Copy link
Copy Markdown
Collaborator

This changes behaviour users already rely on, so it needs a design sign-off from a maintainer before it can merge. A maintainer will post the decision here.
To propose a design, follow the request-for-change process in CONTRIBUTING.md (docs/request-for-change/).

Review result: this review found no blocking findings on this head. The PR adds a draft RFC and one index row. It changes no code. We checked the RFC's claims about today's code against main, and almost all of them hold:

  • record_verdicts stores last_status, last_error and last_failed_at.
  • _annotate_quarantine copies only probeFailures and probeFailing.
  • discovery_featured.json has 8 rows with the listed keys.
  • api_secrets_set is owner-only.

Done well: each claim names a concrete symbol. Stage 2b, the one trust-boundary move, has its own open question and a fallback.

For the security review:

  • Stage 2b lets an owner-started Test resolve a secret:// reference. Today the probe refuses to probe such a server. A maintainer and the security reviewer decide whether to allow this.
  • Stage 2a names PUT /api/mcp/servers/{name} as the env write path. That is the App Kit internal registration route, which is on the strict internal path list. It writes only command, args and env into the Kiro CLI global mcp.json, and it turns the server on. The browser's own edit route, PUT /api/mcp/custom/{name}, keeps the enabled state and disabledTools. The "Who may write" reasoning in section 5.1, section 8 and Q4 should start from that route.

Optional:

@github-actions github-actions Bot added the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Nov 20, 2026
…utton

Stage 1, the per-row Test button, shipped in #38055. A maintainer asked
on #38054 for a request-for-change before the rest is built. This RFC
proposes entering a server key into the vault, showing a row's last
error with a fix hint, and an ordered featured list. It changes no
code.
@RohanK6
RohanK6 force-pushed the crew/conductor/rfc-mcp-connections-center branch from 086744e to 9198c0e Compare November 20, 2026 06:18
@github-actions github-actions Bot added readiness: checking Automated validation is still running and removed readiness: passed Eligible automated validation passed for the current revision merge conflict Branch has merge conflicts with its base — author must resolve before merge labels Nov 20, 2026
@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running labels Nov 20, 2026

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

readiness: passed Eligible automated validation passed for the current revision

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants