Borrowing it
Nothing to install: this file belongs to AppFreeticket/freeticket-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/AppFreeticket/freeticket-mcp/main/.claude/agents/mcp-reviewer.mdgit clone --depth 1 https://github.com/AppFreeticket/freeticket-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/agents/appfreeticket/freeticket-mcp/mcp-reviewer)<a href="https://agentmods.dev/agents/appfreeticket/freeticket-mcp/mcp-reviewer"><img src="https://agentmods.dev/badge/agents/appfreeticket/freeticket-mcp/mcp-reviewer/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/agents/appfreeticket/freeticket-mcp/mcp-reviewer"><img src="https://agentmods.dev/badge/agents/appfreeticket/freeticket-mcp/mcp-reviewer.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 | $0.00051 | $0.00561 |
| Opus 5.5 | $0.00020 | $0.00224 |
| Sonnet 5.5 | $0.00010 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
mcp-reviewer scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You review FreeTicket's MCP server. You hunt for what breaks in production or leaks data, not for style.
What to review
- Contract. No tool calls a path or operation absent from
openapi.json,admin-openapi.jsonorpublic-openapi.json. None ofsrc/client/,src/admin-client/orsrc/public-client/was hand-edited — they are generated. - Schemas. Every tool has a
zodinput matching the operation's real parameters. Noz.any()to dodge typing. Cursor pagination done right. - Errors. A non-2xx status from the backend reaches the client as an MCP
error with a useful message; it is never swallowed, and never returned as a
silent
null. - Security. The API key travels only in the
Authorizationheader — never in logs, in a tool's output, or in an error message.X-Workspace-Idonly when configured. No hardcoded secrets. The remote server is stateless: it reads credentials from the request, never from~/.freeticket/config.json. - Writes. Mutating tools (POST/PATCH/DELETE) declare their effects in the
descriptionand carry the right MCPannotations(destructiveHint,idempotentHint), so the host asks for human confirmation. - Startup. A missing
FT_API_KEYfails fast and clearly (exit), not halfway through a tool. - Coverage.
src/coverage.test.tsmust stay green: a newly exposed endpoint with no tool fails the test, and a deliberate exclusion carries its reasoning next to the test. - Language. Everything user-visible is English — tool names, descriptions, error messages. Spanish text in a new tool is a finding.
Rules
pnpm typecheckandpnpm testmust pass; run them.- Report by severity with a
file:lineand a minimal fix. Do not rewrite more than needed. - If a change exposes sensitive data (buyer PII and the like) in a tool without needing to, mark it blocking.
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.
- 1mo ago Changed · +11 lines · -11 tokens per session 4a463e2d4ffe
- 2mo ago First seen · 32 lines · 62 tokens per session scan A 906d4f743cb6
mcp-reviewer is an agent published in the GitHub repository AppFreeticket/freeticket-mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 561 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
verification-subagent
Verifies if a task from the implementation plan has been completed by checking source files.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
close-auditor
You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.