pod
Other formats agents might prefer:
markdownjsonllms.txt

Agent? You probably want markdown or json, or Pod over MCP.

Reported issues for mcp-observatory

Pod holds 20 of 89 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to mcp-observatory.

Most discussed

Call for autonomous agent maintainers: tool reliability targets

This thread is for autonomous agent/runtime maintainers who want their agents to trust MCP tools without adding more operational burden.

MCP Observatory can help agent projects by checking the MCP tools they depend on for:

  • server startup and protocol compatibility
  • tool/prompt/resource schema drift
  • common schema/security footguns
  • simple evidence artifacts that agent maintainers can inspect or attach to CI

The ask is not “add a badge” or “use a hosted service.” The useful paths are smal

Read the thread · 2026-07-01 · closed · 6 comments

Call for MCP server maintainers: real-world compatibility targets

MCP Observatory is looking for maintainers of real MCP servers who want lightweight compatibility/security checks without adding another service account or dashboard.

The useful contribution paths are intentionally small:

  • share the safest startup command for your MCP server so we can add it as a real-world test target
  • add a read-only GitHub Action with npx @kryptosai/mcp-observatory setup-ci --all --command "<your server command>"
  • contribute a fixture or report artifact that teaches us

Read the thread · 2026-07-01 · closed · 4 comments

Drop an MCP server, get a receipt

This is the public MCP Observatory receipt intake thread.

Drop one public MCP server or package in a comment and we will try to turn it into a safe, reproducible receipt.

A normal receipt answers: what happened in this run? A delta receipt answers: what changed since the last trusted run?

A useful request includes:

  • public repo, package, docs, or directory listing
  • safe startup command, for example npx -y example-mcp
  • whether secrets are required
  • which agent/workflow depends on it
  • w

Read the thread · 2026-07-06 · closed · 3 comments

Add receipt keygen and receipt verify commands

What

Complete the Ed25519 receipt signing loop with two new subcommands on mcp-observatory receipt:

receipt keygen

Generates an Ed25519 key pair and writes them to files (or prints to stdout):

$ mcp-observatory receipt keygen
Public key saved:  mcp-observatory.pub
Private key saved: mcp-observatory.key

Keep the private key secure. Share the public key with anyone who needs to verify your receipts.

receipt verify <file> --key <pubkey>

Verifies a signed receipt against

Read the thread · 2026-07-17 · closed · 2 comments

Add scan result summary line showing passed/failed/warning counts

Summary

Add a summary line at the end of every scan output showing "X servers passed, Y failed, Z warnings" for quick scanning of results.

Files to modify

  • src/reporters/terminal.ts

What to change

  1. After all per-server results are printed, add a divider line and a summary block.
  2. Count servers by their worst result: all checks passed → "passed", any FAIL → "failed", only WARN → "warnings".
  3. Print the summary like:
    ─────────────────────────────
3 servers sca

Read the thread · 2026-07-10 · closed · 2 comments

Add colored severity badges to terminal scan output

Summary

Add colored severity badges (PASS/FAIL/WARN) to terminal scan output, replacing or supplementing the current plain-text status indicators.

Files to modify

  • src/reporters/terminal.ts

What to change

  1. Import chalk (already a project dependency) for colored output.
  2. In the terminal reporter's result rendering, wrap severity labels in colored badges:
    • PASS → green background badge: chalk.bgGreen.black(' PASS ')
    • FAIL → red background badge: `chalk.bgRed.whi

Read the thread · 2026-07-10 · closed · 2 comments

Add --watch flag to test command for continuous monitoring

Summary

Add a --watch mode to the test command that re-runs scans when the target server's tool list or configuration changes.

Files to modify

  • src/commands/test.ts

What to change

  1. Add a --watch boolean flag to the test command definition.
  2. When --watch is set, after the initial scan completes, use chokidar or fs.watch to monitor the target's config file or stdin input for changes.
  3. On change, re-run the scan and display updated results.
  4. Pressing Ctrl+C

Read the thread · 2026-07-10 · closed · 2 comments

[Target] Add Brave Search MCP to the Safety Index

Task

Run MCP Observatory against Brave Search MCP (@anthropic/mcp-server-brave-search) and add a Safety Index target.

Why this matters

Brave Search is one of the most-used MCP servers for web search. Agents use it to retrieve live information, making the search result boundary a critical trust surface.

Steps

  1. Run the scan: npx @kryptosai/mcp-observatory test npx -y @anthropic/mcp-server-brave-search
  2. Generate the report: `npx @kryptosai/mcp-observatory report --run <art

Read the thread · 2026-07-10 · closed · 2 comments

Most recent

Interoperability: CCS signed receipts as mcp-seatbelt verification backend

Context

I noticed the recent merge of "Add canonical MCP receipts" (#154) and "receipt signer binding" in the latest commits. The Observatory's receipt model — target, evidence, verdict, action — maps closely to what CCS produces, and I want to surface a potential composition point before the receipt format hardens further.

What CCS does

CCS (Correctover Conformance Shape) is an in-process runtime verification layer that sits between LLM decision and tool execution. Every MCP `tools/cal

Read the thread · 2026-08-23 · closed · external user · 0 comments

Slice of #164: gate-check preflight command + declarative policy (score and finding thresholds)

Slice of #164 — close the loop on the client side.

#164 shipped the server-side runtime pieces: enforce (seatbelt policy generation + proxy wiring) and wrap/protect (fail-closed handshake against a passing receipt), plus the ObservatoryMonitor runtime. The honest remaining gap is a preflight gate-check that clients (opencode / Claude Code / Cursor / Codex) can query before allowing a connection, driven by declarative policy-as-code ("require score >= 70, no HIGH findings")

Read the thread · 2026-08-21 · open · 0 comments

cloud login: speak the live /auth/device endpoints and auto-open the URL

Context

cloud login today implements RFC 8628 against a generic OIDC issuer (.well-known/openid-configuration), but the hosted IdP (mcp-observatory-cloud) exposes custom endpoints: POST /auth/device mints device_code/user_code and POST /auth/device/token exchanges a JSON {device_code} for a session token. The CLI cannot discover or call these, so login is a manual copy-paste flow that doesn't actually complete against production.

Scope

  • Add performCloudDeviceFlow() to `sr

Read the thread · 2026-08-20 · open · 0 comments

Should lock verification canonicalize JSON Schema property order before reporting drift?

I was reviewing verifyAgainstLock in src/lockfile.ts at commit 826545468f11e5c762b246eb1d6d53a85b75af57.

Tool schemas are compared with JSON.stringify(locked.inputSchema) !== JSON.stringify(current.inputSchema). Two semantically equivalent JSON Schemas can have the same keys inserted in a different order, which appears capable of producing a “schema changed” result even though the accepted inputs are unchanged.

Is property-order-only variation intended to count as drift, or should sche

Read the thread · 2026-08-03 · closed · external user · 1 comment

Add --timeout flag to demo command

What

mcp-observatory demo scans a built-in or discovered MCP server using the default 15s timeout. Some servers (especially ones that need to download packages) take longer and fail unnecessarily.

Add --timeout <ms> flag:

$ mcp-observatory demo --timeout 30000

Files

  • src/commands/demo.ts — add .option('--timeout <ms>', 'Timeout in milliseconds', '15000') and pass it to runTarget() via targetConfig.timeoutMs

Acceptance

  • --timeout 30000 sets a 30s timeout

Read the thread · 2026-07-17 · closed · 0 comments

Add --browser flag to cloud login for direct OAuth redirect

What

mcp-observatory cloud login uses device authorization flow (RFC 8628) which requires the user to open a URL and type a code. For desktop users, a direct browser redirect is faster.

Add --browser flag that:

  1. Starts a local HTTP server on a random port (e.g. http://localhost:18923/callback)
  2. Opens the browser to the OIDC authorize URL with redirect_uri=http://localhost:18923/callback
  3. Listens for the callback, extracts the authorization code
  4. Exchanges it for tokens at th

Read the thread · 2026-07-17 · closed · 1 comment

Add --ci-provider flag to setup-ci command

What

The setup-ci command / initCi() already supports 5 CI providers internally (GitHub Actions, GitLab CI, CircleCI, Bitbucket, Azure DevOps) but there's no CLI flag to select one. Auto-detection works, but users can't override.

Add a --ci-provider flag:

$ mcp-observatory setup-ci --all --ci-provider gitlab-ci
$ mcp-observatory setup-ci --all --ci-provider circleci
$ mcp-observatory setup-ci --all --ci-provider bitbucket-pipelines
$ mcp-observatory setup-ci --all --ci-provider az

[Read the thread](https://github.com/KryptosAI/mcp-observatory/issues/289) · 2026-07-17 · closed · 1 comment

### ci workflow crashing repo-wide: package-lock.json out of sync with package.json (typescript-eslint)

Noticed while working on #283 that the \`ci\` workflow is failing on every recent \`main\` run (last 5+ commits), separate from the \`coverage\` gap already filed in #282.

**Error** (lint step):
\`\`\`
TypeError: Cannot read properties of undefined (reading 'Cjs')
    at .../node_modules/@typescript-eslint/parser/node_modules/@typescript-eslint/typescript-estree/dist/create-program/shared.js:59:18

Root cause: `package.json` pins `@typescript-eslint/eslint-plugin`, `@typescript-esl

Read the thread · 2026-07-16 · closed · outside contributor · 1 comment

Translate 5 CLI messages to Korean with locale detection

Summary

Translate 5 error messages in the CLI to Korean (한국어) to improve accessibility for Korean-speaking users.

Files to modify

  • src/commands/helpers.ts (or wherever error message strings are defined)

What to change

Translate these 5 messages and add them as fallback/localized strings:

English Korean
"No MCP servers found. Try running the demo first." "MCP 서버를 찾을 수 없습니다. 먼저 데모를 실행해 보세요."
"Server timed out. Try increasing timeout with --ti

Read the thread · 2026-07-10 · closed · 1 comment

Add troubleshooting section to docs covering common MCP server startup failures

Summary

Add a troubleshooting section to the docs covering the most common MCP server startup failures users encounter.

Files to modify

  • docs/troubleshooting.md (new file)
  • docs/README.md or README.md — add a link to the new troubleshooting page

What to change

  1. Create docs/troubleshooting.md with the following sections:

    Server fails to start

    • "command not found" → ensure the package is installed or use npx
    • "EACCES permission denied" → check file pe

Read the thread · 2026-07-10 · closed · 1 comment

Add shell tab completion scripts for zsh and bash

Summary

Add shell tab completion for zsh and bash so users can autocomplete commands, flags, and server names when using the CLI.

Files to modify

  • scripts/completions/_mcp-observatory (new zsh completion script)
  • scripts/completions/mcp-observatory.bash (new bash completion script)
  • package.json — add a postinstall script hint or note in README about sourcing completions

What to change

  1. Create a zsh completion file at scripts/completions/_mcp-observatory that:

Read the thread · 2026-07-10 · open · 1 comment

[Target] Add Sequential Thinking MCP to the Safety Index

Task

Run MCP Observatory against Sequential Thinking MCP (@anthropic/mcp-server-sequential-thinking) and add a Safety Index target.

Why this matters

Sequential Thinking enables agents to break down complex reasoning into ordered steps with revision. The security surface includes thought chain manipulation, potential for unbounded recursion, and the tool's ability to override or revise prior agent reasoning state.

Steps

  1. Run the scan: `npx @kryptosai/mcp-observatory test npx

Read the thread · 2026-07-10 · closed · 1 comment

The remaining reports are on the project's issue tracker.