What is legal-open-mcp-server AGENTS.md?

A project instruction file for an MCP server that supports legal research and drafting focused on Indian law. It documents the code layout, security rules, commands, and project conventions.

Use it when an agent needs to understand, modify, test, or deploy the legal-mcp project. It covers areas such as legal citations, data sources, authentication, settings, templates, and OpenShift deployment.

It gives coding agents the project-specific rules they need, so they can work in the right files and verify changes correctly. It also helps prevent secrets from being committed and directs security issues to private reports.

How bsahane/legal-open-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to bsahane/legal-open-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.

Copy the file

curl -O https://raw.githubusercontent.com/bsahane/legal-open-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/bsahane/legal-open-mcp-server

Made for: Codex, OpenCode.

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/bsahane/legal-open-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/bsahane/legal-open-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/bsahane/legal-open-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/bsahane/legal-open-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bsahane/legal-open-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/bsahane/legal-open-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 773 This file is loaded in full into every session.

When invoked 773 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	$0.00773	$0.00773
Opus 5.5	$0.00309	$0.00309
Sonnet 5.5	$0.00155	$0.00155
Haiku 4.5	$0.00077	$0.00077

Measured 2mo ago against content hash 13c70590a2f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

legal-open-mcp-server 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 2mo 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

legal-mcp

MCP server and legal research/drafting assistant for Indian law. Python 3.12+, FastMCP 2, FastAPI, Pydantic, DuckDB, asyncpg. Built on the Red Hat template-mcp-server pattern. Architecture and docs live in docs/.

Policy

Never commit secrets, API keys, or .env — use environment variables via .env.example.
Security vulnerabilities go through GitHub Security Advisories, never public issues.

Where things are

MCP tool modules: legal_mcp_server/src/tools/ — each file exports a TOOLS list registered in legal_mcp_server/src/mcp.py
Domain logic (citations, limitation, criminal codes): legal_mcp_server/src/domain/
Data sources (Indian Kanoon, open judgments, eCourts, embeddings): legal_mcp_server/src/sources/
OAuth flow: legal_mcp_server/src/oauth/
Settings and env loading: legal_mcp_server/src/settings.py
Jinja templates and manifest: legal_mcp_server/src/templates/
Bundled corpus data: data/; build with make corpus
Deployment (OpenShift): deployment/openshift/
Tool docstring format guide: legal_mcp_server/src/tools/README.md

Running and verifying

Use uv run pytest (or make test) — do not run bare pytest, which resolves outside the project venv.
CI also runs pre-commit run --all-files (ruff, mypy, pydocstyle, bandit); make test alone does not cover this — run make pre-commit locally before pushing.
Coverage must stay ≥ 80% (--cov-fail-under=80).
Local server: make local (port 5001). Container: make container (podman compose).
Corpus must be built before case-law tools work: make corpus.

Conventions that differ from defaults

Every new tool function must be added to its module's TOOLS list and given an entry in legal_mcp_server/src/tool_annotations.py — a missing annotation logs a warning at startup.
Tool docstrings use the structured TOOL_NAME=… / DISPLAY_NAME=… / USECASE=… format described in legal_mcp_server/src/tools/README.md, not plain Google-style.
All tool functions return Dict[str, Any] with a status field ("success" or "error").
Logging uses legal_mcp_server.utils.pylogger.get_python_logger(), not stdlib logging directly.
Google-convention docstrings enforced by pydocstyle; double-quote strings enforced by Ruff.

Read the full file on GitHub · 48 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.

2mo ago First seen · 48 lines · 773 tokens per session scan A 13c70590a2f9

Subscribe to this mod's changes

legal-open-mcp-server AGENTS.md is an instructions file published in the GitHub repository bsahane/legal-open-mcp-server (1 stars, last pushed 18d ago), licensed Apache-2.0. It adds 773 tokens to every session, about $0.0031 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.

Legal and compliance

legal-open-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
legal-open-mcp-server AGENTS.mdbsahane/legal-open-mcp-server	Instructions file	1	18d ago	Apache-2.0	A	773	Codex, OpenCode
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

legal-open-mcp-server: Instructions file for Codex