Borrowing it
Nothing to install: this file belongs to saagpatel/mcp-trust. 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/saagpatel/mcp-trust/main/AGENTS.mdgit clone --depth 1 https://github.com/saagpatel/mcp-trustWrote 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/instructions/saagpatel/mcp-trust/agents-md)<a href="https://agentmods.dev/instructions/saagpatel/mcp-trust/agents-md"><img src="https://agentmods.dev/badge/instructions/saagpatel/mcp-trust/agents-md/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/instructions/saagpatel/mcp-trust/agents-md"><img src="https://agentmods.dev/badge/instructions/saagpatel/mcp-trust/agents-md.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 | $0.01232 | $0.01232 |
| Opus 5.5 | $0.00493 | $0.00493 |
| Sonnet 5.5 | $0.00246 | $0.00246 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
mcp-trust AGENTS.md 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 13d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Trust Registry
Purpose
MCP Trust Registry is a neutral public trust registry for MCP servers. Its product loop is "check before you connect": register public MCP servers, scan them with a pluggable engine, normalize results into an A-F danger grade plus a transparency signal, persist the record, and serve it through a public API, web catalog, and README badge endpoint.
The scanner is a replaceable backend. The durable product is the public catalog,
stable lookup API, trust-grade normalization, and author badge distribution
loop. The real engine adapter wraps mcp-audits; StubEngine keeps the system
testable without launching untrusted code.
Layout
src/mcp_trust/api/: FastAPI service and public API projection.src/mcp_trust/core/: domain models, grading, governance, and provenance.src/mcp_trust/engine/: scan engine contract, stub, and optional real adapter.src/mcp_trust/store/: SQLite schema and repositories.src/mcp_trust/site/: static site and badge generation.scripts/,deploy/,docker/,docs/: operator tooling, deployment assets, scan environments, and product/runbook documentation.contracts/web-release-readback-v1/: additive readback schemas and policy.
SPEC.md is the product and module-boundary contract. LAUNCH.md and the
operator runbook describe separately authorized operator workflows.
Setup
Use Python 3.12 or newer. .python-version pins Python 3.15.0, and uv.lock
locks the project and development dependencies. Install the pinned uv version
(0.13.0) and run:
make setup
This installs the core and development dependencies. It does not install the
optional mcp-audits engine extra or enable real-server/Docker scans.
Checks
Run the aggregate local gate with:
make check
It checks the lockfile, Ruff lint and formatting, Pyright, deterministic pytest coverage, and package builds. Opt-in integration and Docker tests remain off. See the README Quickstart and local development instructions for focused test commands and a stub-only preview.
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.
- 13d ago Changed · -14 lines · -360 tokens per session 2270f9bd2f5d
- 23d ago Changed · -16 lines · -90 tokens per session c0aa8c06ea23
- 1mo ago Changed · +14 lines · +177 tokens per session 068715a3ebba
- 1mo ago First seen · 135 lines · 1,505 tokens per session scan A 23d4f2cd6bec
mcp-trust AGENTS.md is an instructions file published in the GitHub repository saagpatel/mcp-trust (0 stars, last pushed 3d ago), licensed MIT. It adds 1,232 tokens to every session, about $0.0049 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.