mcp-contract-reviewer

mcp-contract-reviewer is an agent for coding agents from tacticlaunch/mcp-linear. It costs 22 tokens per session (220 once invoked), scanned A, original, MIT.

A review agent for checking changes to mcp-linear's MCP tool contracts. A contract is the agreed input and output shape that a tool exposes to callers.

In plain words
What is it for?
Use it to review Linear changes for nullability, enums, numeric limits, normalization, handler behavior, registrations, documentation, and justified GraphQL fallbacks.
Why use it?
It catches mismatches between schemas, runtime validation, service output, registrations, and tests that could cause clients to call tools incorrectly.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/tacticlaunch/mcp-linear/mcp-contract-reviewer
Clone the repo
git clone --depth 1 https://github.com/tacticlaunch/mcp-linear

Wrote 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.

agentmods badge for mcp-contract-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/tacticlaunch/mcp-linear/mcp-contract-reviewer.svg)](https://agentmods.dev/agents/tacticlaunch/mcp-linear/mcp-contract-reviewer)
Your own site
<a href="https://agentmods.dev/agents/tacticlaunch/mcp-linear/mcp-contract-reviewer"><img src="https://agentmods.dev/badge/agents/tacticlaunch/mcp-linear/mcp-contract-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 220 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.00220
Opus 5 $0.00011 $0.00110
Sonnet 5 $0.00004 $0.00044
Haiku 4.5 $0.00002 $0.00022

Measured 5d ago against content hash 38d000ef15f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-contract-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 5d 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.

.github/agents/mcp-contract-reviewer.agent.md · 24 lines

What it actually says

You are a reviewer for mcp-linear pull requests and diffs.

Your primary concern is MCP contract correctness, not style nitpicks.

Review checklist:

  1. Compare each input_schema to the corresponding type guard.
  2. Compare each output_schema to the actual normalized service output.
  3. Check nullable fields, enum values, and positive integer constraints.
  4. Check that handlers validate before delegating and do not add business logic.
  5. Check that every public tool is registered in both index files.
  6. Check that TOOLS.md stays in sync with the exposed tool surface.
  7. Check whether direct GraphQL usage is justified by an SDK limitation or stale generated query.
  8. Check for missing focused tests around new behavior and negative cases.

Output findings first, ordered by severity, with exact file references.

Changes

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.

  1. 5d ago First seen · 24 lines · 22 tokens per session scan A 38d000ef15f2

Subscribe to this mod's changes

mcp-contract-reviewer is an agent published in the GitHub repository tacticlaunch/mcp-linear (146 stars, last pushed 6d ago), licensed MIT. It adds 22 tokens to every session and 220 once invoked, about $0.0001 per session on Opus 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 2026-08-30.