What is thesma-mcp CLAUDE.md?

A project instruction file for Claude Code, an AI coding assistant. It explains the project, its Python tools, folder layout, and required ways of working.

Use it to guide work on the Thesma MCP server, which connects AI assistants to SEC EDGAR company-filing data. It also requires task tracking with td and identifies the testing, formatting, and type-checking tools.

It gives the assistant the project context and rules it needs before changing code. This reduces confusion about where code belongs and how tasks should be tracked.

How thesma-dev/thesma-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thesma-dev/thesma-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.

Copy the file

curl -O https://raw.githubusercontent.com/thesma-dev/thesma-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/thesma-dev/thesma-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/thesma-dev/thesma-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/thesma-dev/thesma-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/thesma-dev/thesma-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thesma-dev/thesma-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/thesma-dev/thesma-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thesma-dev/thesma-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,021 This file is loaded in full into every session.

When invoked 1,021 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01021	$0.01021
Opus 5	$0.00511	$0.00511
Sonnet 5	$0.00204	$0.00204
Haiku 4.5	$0.00102	$0.00102

Measured 8d ago against content hash 4fc43b80713b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

thesma-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 8d 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.

CLAUDE.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

MANDATORY: Use td for Task Management

You must run td usage --new-session at conversation start (or after /clear) to see current work. Use td usage -q for subsequent reads.

Project

Thesma MCP Server — MCP server that gives AI assistants native access to Thesma's SEC EDGAR data.

The MCP server is a thin translation layer: it receives MCP tool calls from AI assistants (Claude, Cursor, ChatGPT), translates them into Thesma REST API requests, and formats the responses as structured text for LLM consumption. It has no database, no data processing, and no state beyond an in-memory ticker cache.

Stack

Python 3.12+, MCP Python SDK (FastMCP), httpx
Ruff for linting/formatting, mypy strict mode
pytest + pytest-asyncio for testing, respx for HTTP mocking

Key directories

Directory	Purpose
`src/thesma_mcp/`	Server code (client, resolver, formatters, server)
`src/thesma_mcp/tools/`	MCP tool definitions
`tests/`	pytest tests

Linked repos

Docs repo: /Users/willcodejavaforfood/Documents/gov-data-docs — product specifications and implementation prompts
API repo: /Users/willcodejavaforfood/Documents/GitHub/govdata-api — Thesma REST API that this MCP server wraps

Development

Setup

python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
cp .env.example .env  # then fill in THESMA_API_KEY

Testing

make test — run all tests
make check — lint + type-check + test (all quality gates)

Port

HTTP transport: 8200 (default, overridden by PORT env var on Railway)

Deployment

The MCP server is deployed on Railway via Streamable HTTP.

Dockerfile: Does NOT set THESMA_MCP_TRANSPORT — must be passed at runtime
Railway env vars:
- THESMA_MCP_TRANSPORT=http (required)
- PORT (set by Railway automatically)
- SUPABASE_URL + SUPABASE_SERVICE_KEY (enables OAuth via Supabase Auth)
- MCP_BASE_URL (OAuth issuer URL, e.g. https://thesma-mcp-production.up.railway.app)
- THESMA_API_KEY (optional — default fallback key if no OAuth / no Bearer header)
Health check: GET /health on the Railway domain
Auto-deploy not wired — see memory feedback_gh_account for why. Deploys happen via railway up from local CLI.

Read the full file on GitHub · 105 lines

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.

8d ago First seen · 105 lines · 1,021 tokens per session scan A 4fc43b80713b

Subscribe to this mod's changes

thesma-mcp CLAUDE.md is an instructions file published in the GitHub repository thesma-dev/thesma-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,021 tokens to every session, about $0.0051 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.

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

thesma-mcp: Instructions file for Claude Code