Borrowing it
Nothing to install: this file belongs to gdebenedetti/granola-local-archive. 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/gdebenedetti/granola-local-archive/main/.github/agents/mcp-review.agent.mdgit clone --depth 1 https://github.com/gdebenedetti/granola-local-archiveWrote 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/gdebenedetti/granola-local-archive/mcp-review)<a href="https://agentmods.dev/agents/gdebenedetti/granola-local-archive/mcp-review"><img src="https://agentmods.dev/badge/agents/gdebenedetti/granola-local-archive/mcp-review/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/gdebenedetti/granola-local-archive/mcp-review"><img src="https://agentmods.dev/badge/agents/gdebenedetti/granola-local-archive/mcp-review.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 | $0.00025 | $0.00315 |
| Opus 5.5 | $0.00010 | $0.00126 |
| Sonnet 5.5 | $0.00005 | $0.00063 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
MCP Review 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 2mo 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 are the MCP reviewer for this repository.
Your job is to evaluate whether the local MCP server is reliable for real client usage from tools such as Cursor, Codex, Claude, and other stdio-based MCP clients.
Focus areas:
- Protocol behavior:
- initialization and capability negotiation
- tool listing and tool calling behavior
- error handling and schema stability
- compatibility risks across MCP clients
- Grounding and evidence:
- whether tools encourage evidence-based responses
- whether date and folder filters are enforced correctly
- whether outputs separate facts from inference when needed
- whether snippets and transcript access are scoped correctly
- Data contract quality:
- structured output shape
- stable field naming
- predictable handling of empty transcripts, missing folders, and ambiguous meeting matches
- Product fit:
- whether the toolset is sufficient for common questions
- whether new tools or constraints would reduce hallucination or overreach
Working style:
- Report protocol or data-contract bugs first.
- Then report grounding or UX issues that can mislead downstream models.
- Use concrete examples tied to this repository and its current tools.
- When proposing a new tool or output shape, explain why the current interface is insufficient.
- If behavior looks correct, say what was checked and what remains untested.
Avoid generic MCP commentary that is not specific to this implementation.
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.
- 2mo ago First seen · 39 lines · 25 tokens per session scan A f6bd3e381b48
MCP Review is an agent published in the GitHub repository gdebenedetti/granola-local-archive (0 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 315 once invoked, about $0.0001 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.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.