Borrowing it
Nothing to install: this file belongs to navisbio/AACT_clinicaltrials_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/navisbio/AACT_clinicaltrials_MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/navisbio/AACT_clinicaltrials_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/instructions/navisbio/aact_clinicaltrials_mcp/claude-md)<a href="https://agentmods.dev/instructions/navisbio/aact_clinicaltrials_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/navisbio/aact_clinicaltrials_mcp/claude-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/navisbio/aact_clinicaltrials_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/navisbio/aact_clinicaltrials_mcp/claude-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 | $0.00567 | $0.00567 |
| Opus 5.5 | $0.00227 | $0.00227 |
| Sonnet 5.5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
AACT_clinicaltrials_MCP CLAUDE.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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MCP (Model Context Protocol) server that gives AI assistants read-only access to the AACT clinical trials database (ClinicalTrials.gov). It exposes three tools: list_tables, describe_table, and read_query over the FastMCP framework, connecting to a remote PostgreSQL database.
Commands
# Run the server
uv run mcp-server-aact
# Run tests
uv run pytest
# Type checking
uv run pyright aact_mcp/
# Install dependencies (including dev)
uv sync
# Docker build and run
docker build -t mcp-server-aact .
docker run --rm -i --env DB_USER=X --env DB_PASSWORD=Y mcp-server-aact
Architecture
Source files in aact_mcp/, each with a single responsibility:
- server.py — FastMCP server definition and tool handlers. Loads
.envat startup, creates theAACTDatabaseinstance and theFastMCPapp. All tool handlers are async and useContextfor structured logging/progress. - database.py —
AACTDatabaseclass wrapping psycopg2. Connects toaact-db.ctti-clinicaltrials.orgthrough a small pool with a connect timeout and a statement timeout. Fails hard ifDB_USER/DB_PASSWORDenv vars are missing. - query_guard.py — Parses user SQL and rejects anything other than a single read-only SELECT, WITH, or EXPLAIN statement.
- models.py — Pydantic models (
TableInfo,ColumnInfo,QueryResult) used as tool return types.
Entry point: aact_mcp/__init__.py exports main() which calls mcp.run().
Key Design Decisions
- Read-only enforcement:
query_guard.pyparses SQL before it is sent. The PostgreSQL session is read-only as well, and dynamic table or column names usepsycopg2.sql.Identifier. - Fail-hard: No silent defaults for missing config. Missing credentials raise immediately.
- Row limiting: Default 25 rows per query, configurable via
max_rowsparameter. - Remote database: Connects directly to AACT's hosted PostgreSQL — no local DB setup needed. Users register at https://aact.ctti-clinicaltrials.org for credentials.
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 · +9 tokens per session 310d433f6b69
- 1mo ago Changed · +1 lines · +28 tokens per session e4ca43ae3735
- 2mo ago First seen · 51 lines · 530 tokens per session scan A 830b91e2b96a
AACT_clinicaltrials_MCP CLAUDE.md is an instructions file published in the GitHub repository navisbio/AACT_clinicaltrials_MCP (21 stars, last pushed 13d ago), licensed MIT. It adds 567 tokens to every session, about $0.0023 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 2026-08-30.
AACT_clinicaltrials_MCP CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AACT_clinicaltrials_MCP CLAUDE.mdnavisbio/AACT_clinicaltrials_MCP | Instructions file | 21 | 13d ago | MIT | A | 567 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |