Borrowing it
Nothing to install: this file belongs to financial-reports/financial-reports-mcp-server. 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/financial-reports/financial-reports-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/financial-reports/financial-reports-mcp-serverWrote 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/financial-reports/financial-reports-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/financial-reports/financial-reports-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/financial-reports/financial-reports-mcp-server/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/financial-reports/financial-reports-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/financial-reports/financial-reports-mcp-server/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 | $0.01836 | $0.01836 |
| Opus 5 | $0.00918 | $0.00918 |
| Sonnet 5 | $0.00367 | $0.00367 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
financial-reports-mcp-server AGENTS.md scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**⚠️ Merging to `main` does not deploy.** `.github/workflows/` here holds only `ci.yml` — no build, no deploy. The build+deploy job is `generate_sdks.yml` in the private companion repo `financial-reports/web`, and it is How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent-facing guide for the FinancialReports MCP server repo. This file is the cross-harness standard (agents.md) — read by Codex, Cursor, Kilo Code, Gemini CLI, opencode, Zed, Aider, and others. Claude Code reads it too (via CLAUDE.md, which imports this file).
What this repo is
The official remote Model Context Protocol server for the FinancialReports API. It exposes 16 LLM-callable tools by default (regulatory filings, financials, company data, batch identifier resolution, in-filing search, plus guide tools); set MCP_FULL_SURFACE=1 to restore the full 46-tool surface (adds ISIC industry classification, watchlists, webhooks, company merges, security listings, and the rest of the reference data). The OpenAPI-derived tools are generated from a committed, reviewed schema snapshot (scripts/openapi.snapshot.json, pinned via FR_PIN_SCHEMA=1 in CI and the Docker build). It runs as a FastAPI host that mounts a FastMCP server behind an AWS Cognito OAuth proxy. Production: https://mcp.financialfilings.com/mcp.
The one rule that matters: src/ is generated
src/financial_reports_mcp.py is auto-generated and git-ignored. Never edit it — your changes are overwritten on the next build.
To change tool behavior, descriptions, or the server itself:
- Edit
scripts/generate_mcp_tools.py(server scaffolding, theFILE_HEADER_TEMPLATE, tool template, landing-page HTML) and/orscripts/tool_overrides.yaml(per-toolwhen_to_use/when_not_to_use/examplesthat improve LLM ergonomics). - Regenerate:
make regen(orpython scripts/generate_mcp_tools.py). - Run tests, then commit.
The tool catalog in README.md (between the AUTO-GENERATED TOOL LIST markers) is also produced by the generator — don't hand-edit it.
Accepted exception: synthetic (non-schema) emitted code
Most tools are generated from the OpenAPI schema, but some emitted code is not schema-derived and lives as inline *_BLOCK string templates inside scripts/generate_mcp_tools.py: the MCP resources (RESOURCES_BLOCK), prompts (PROMPTS_BLOCK), the guide tools (GUIDE_TOOLS_BLOCK), and the in-filing search tool (MARKDOWN_SEARCH_TOOL_BLOCK). These are still emitted into src/ by the generator like everything else — they are NOT hand-edits to src/, and the "never edit src/" rule applies to them unchanged. Edit them in the generator. Trade-off worth knowing: an inline-string body isn't seen by ruff/black/mypy in source form (it is import/type-checked when the generated module loads in the test suite). Extracting all *_BLOCK bodies into separate lintable template files the generator reads is a reasonable future cleanup — do it for all of them or none, to keep a single pattern.
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.
- 9d ago First seen · 70 lines · 1,836 tokens per session scan A ef3413f64586
financial-reports-mcp-server AGENTS.md is an instructions file published in the GitHub repository financial-reports/financial-reports-mcp-server (2 stars, last pushed 7d ago), licensed MIT. It adds 1,836 tokens to every session, about $0.0092 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.