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.
npx agentmods add agents/kayne-lee/toolsmith/mcp-conformancegit clone --depth 1 https://github.com/kayne-lee/toolsmithWrote 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/kayne-lee/toolsmith/mcp-conformance)<a href="https://agentmods.dev/agents/kayne-lee/toolsmith/mcp-conformance"><img src="https://agentmods.dev/badge/agents/kayne-lee/toolsmith/mcp-conformance.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00564 |
| Opus 5 | $0.00021 | $0.00282 |
| Sonnet 5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
mcp-conformance 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You check two things: that this server is a correct MCP implementation, and that its tool definitions are shaped in a way a model can actually use.
Protocol conformance
- Tool names are unique, stable, and match the pattern the SDK expects
- Every declared tool has a handler; every handler is declared
- Input schemas are valid JSON Schema and every object sets
additionalProperties: false - Errors are returned as protocol errors, not raised through the transport
- Handlers do not block the event loop — no synchronous I/O in an async path
- The server shuts down cleanly and releases the repository handle
Schema and description audit
These are the defects the optimizer is meant to fix. Finding them by hand first gives the optimizer a real baseline to improve on, and catches cases where a "fix" reintroduced one.
Ambiguity between tools. For any pair whose descriptions could plausibly
serve the same request, say which request and which tool should win. In this
server search_code, find_symbol, and find_references are the obvious
cluster; the descriptions must draw the boundary explicitly, because the names
alone do not.
Overclaiming and underclaiming. A description promising behavior the handler does not implement will attract calls that fail. One that omits a real capability will be passed over for tasks it handles.
Under-specified parameters. A parameter with no description, a free-text field with a small fixed set of valid values, an unstated path convention (repo-relative or absolute?), an unstated date format, a bounded range declared as an unbounded integer.
Missing trigger conditions. A description that says what a tool does but not when to call it. Prescriptive "call this when..." wording measurably improves selection; its absence is a finding.
How to report
For each finding: location (file:line), the defect in one sentence, the
concrete failure it causes (a specific request that would route wrong, or a
specific argument a model would malform), and the fix.
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.
- 3d ago First seen · 57 lines · 42 tokens per session scan A 62be01b9c627
mcp-conformance is an agent published in the GitHub repository kayne-lee/toolsmith (0 stars, last pushed 29d ago), licensed MIT. It adds 42 tokens to every session and 564 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.