Borrowing it
Nothing to install: this file belongs to naveed949/kaia-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/naveed949/kaia-mcp/main/.cursor/skills/verify-kaia-mcp/SKILL.mdgit clone --depth 1 https://github.com/naveed949/kaia-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/naveed949/kaia-mcp/verify-kaia-mcp)<a href="https://agentmods.dev/skills/naveed949/kaia-mcp/verify-kaia-mcp"><img src="https://agentmods.dev/badge/skills/naveed949/kaia-mcp/verify-kaia-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/naveed949/kaia-mcp/verify-kaia-mcp"><img src="https://agentmods.dev/badge/skills/naveed949/kaia-mcp/verify-kaia-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00155 | $0.03002 |
| Opus 5.5 | $0.00062 | $0.01201 |
| Sonnet 5.5 | $0.00031 | $0.00600 |
| Haiku 4.5 | $0.00015 | $0.00300 |
Grade A, and why
verify-kaia-mcp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Verify the kaia-mcp HTTP MCP connector (stateless MCP 2026-07-28 transport, Origin validation, OAuth PKCE, RFC 8707 resource/audience, RFC 9728 Bearer challenges incl. 403 insufficient_scope, RFC 9207 iss, s How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify kaia-mcp
Primary surface: stateless Streamable HTTP MCP (POST / only, no sessions) plus the in-process demo OAuth/OIDC endpoints. Stdio exists for local desktop but is not the partner path and is not driven here.
Repo-documented start: npm run build then node dist/bin/kaia-mcp.js --transport http --port <PORT> (same as npm start with --transport http). Partner default is KAIA_AUTH_MODE=required. Health is GET /health. Ready means that URL returns JSON status=ok.
Two instances may run side by side if each uses its own port and RUN_ID. Never attach to a server you did not launch.
Launch
From the repo root, with a unique run id:
export KAIA_VERIFY_RUN_ID="manual-$(date +%Y%m%dT%H%M%S)-$$"
.cursor/skills/verify-kaia-mcp/helpers/launch.sh
launch.sh rebuilds dist/ (npm run build, log in the instance dir) on every launch so a stale build is never verified, binds an ephemeral port on this host, starts node dist/bin/kaia-mcp.js --transport http --port <PORT> with KAIA_AUTH_MODE=required, KAIA_ALLOW_UNSAFE_WALLET unset, LOG_LEVEL=debug (so the leak check covers the noisiest log path), KAIA_ACCESS_TOKEN_TTL_SECONDS=${KAIA_VERIFY_TOKEN_TTL:-20} (so expiry is drivable), an in-memory signing key (KAIA_VERIFY_KEY_MODE=file persists the key and revocation denylist under the instance dir instead), a random per-run KAIA_INTROSPECTION_CLIENT_SECRET (written to evidence/<run-id>/introspection.secret.json, mode 0600), and KAIA_PUBLIC_URL, KAIA_ALLOWED_ORIGINS, KAIA_OAUTH_LEGACY_AUDIENCE/KAIA_OAUTH_AUDIENCE, KAIA_OAUTH_REQUIRE_RESOURCE and KAIA_OAUTH_PREVIOUS_SIGNING_KEY_FILES pinned empty (so a shell export cannot change the issuer or audience: issuer = canonical resource URI = token aud = http://127.0.0.1:<PORT>), and waits until GET /health succeeds.
Ready signal: stdout contains ready: GET http://127.0.0.1:<PORT>/health returned status ok. Instance metadata is /tmp/kaia-mcp-verify-$KAIA_VERIFY_RUN_ID/instance.json (pid, port, issuer, logFile, tokenTtlSeconds, introspectionSecretFile, launchKeyMode, keyMode). The server env is in server.env (mode 0600) next to it.
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- features/bearer-challenges.md 3.4 KB
- features/device-flow.md 2.1 KB
- features/fail-closed-auth.md 7.1 KB
- features/generate-wallet-gated.md 1.8 KB
- features/jwt-access-tokens.md 4.2 KB
- features/oauth-pkce-scoped-tools.md 4.2 KB
- features/protocol-2026-07-28.md 5.6 KB
- features/README.md 6.1 KB
- features/resource-indicators.md 4.1 KB
- features/revocation-restart.md 6.8 KB
- features/stateless-multi-instance.md 7.8 KB
- features/stateless-transport.md 5.4 KB
- features/token-introspection.md 3.6 KB
- helpers/cleanup.sh 1.5 KB runs code
- helpers/common.sh 4.3 KB runs code
- helpers/doctor.sh 3.9 KB runs code
- helpers/drive.sh 99 KB runs code
- helpers/launch.sh 2.6 KB runs code
- helpers/restart.sh 1.7 KB runs code
- helpers/token-leak-check.sh 2.0 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago Changed · +15 lines · +97 tokens per session 1ea1e87a9fe1
- 12d ago First seen · 99 lines · 58 tokens per session scan A 4c7020f76a65
verify-kaia-mcp is a skill published in the GitHub repository naveed949/kaia-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 155 tokens to every session and 3,002 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-07.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.