What is mcp-docs-server AGENTS.md?

A set of instructions for AI coding assistants working on a Mapbox documentation server. The server provides access to Mapbox documentation and reference material through MCP, a standard way for assistants to use external tools and resources.

It helps assistants understand and modify the server, follow its TypeScript and testing setup, and work with its documentation resources and tools.

It gives an assistant the project context, structure, technology choices, and important coding patterns needed to work safely in the repository.

mcp-docs-server AGENTS.md — Instructions file by mapbox

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/mapbox/mcp-docs-server/agents-md

Clone the repo

git clone --depth 1 https://github.com/mapbox/mcp-docs-server

Made for: Codex, OpenCode.

Per session 932 This file is loaded in full into every session.

When invoked 932 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00932	$0.00932
Opus 5	$0.00466	$0.00466
Sonnet 5	$0.00186	$0.00186
Haiku 4.5	$0.00093	$0.00093

Measured yesterday against content hash 8a20ce34231b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-docs-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 yesterday.

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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Instructions for Mapbox MCP Documentation Server

Note: If you're using Claude Code specifically, see CLAUDE.md instead. This file is for general AI coding assistants (Cursor, Continue, Aider, Copilot, etc.).

What This Project Does

This is an MCP (Model Context Protocol) server that gives AI assistants access to Mapbox documentation and reference materials. No Mapbox access token is required for most tools — it is a documentation-only server.

Tech Stack

Runtime: Node.js 22+
Language: TypeScript (strict mode)
Build: tshy (dual ESM/CJS output)
Testing: Vitest
Package Manager: npm

Project Structure

src/
├── index.ts                    # MCP server entry point
├── config/toolConfig.ts        # CLI argument parser
├── constants/                  # Static data (API endpoint definitions)
├── resources/                  # MCP resource implementations
│   ├── BaseResource.ts         # Abstract base class
│   ├── resourceRegistry.ts     # Resource registration
│   ├── utils/docParser.ts      # Shared doc parsing utilities
│   └── */                      # Individual resource implementations
├── tools/                      # MCP tool implementations
│   ├── BaseTool.ts             # Abstract base class
│   ├── toolRegistry.ts         # Tool registration
│   └── */                      # Individual tool implementations
└── utils/
    ├── httpPipeline.ts         # HTTP pipeline (User-Agent, caching, retry)
    ├── types.ts                # Shared types
    └── versionUtils.ts

test/                           # Mirrors src/ structure

Critical Patterns

Tool Architecture

All tools extend BaseTool<InputSchema, OutputSchema> (not MapboxApiBasedTool — that is in a different repo)
execute(input) receives only the validated input — no accessToken or context parameters
If a tool needs a Mapbox token, it must be a field in the input schema
Register tools in src/tools/toolRegistry.ts

Read the full file on GitHub · 106 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.

yesterday First seen · 106 lines · 932 tokens per session scan A 8a20ce34231b

Subscribe to this mod's changes

mcp-docs-server AGENTS.md is an instructions file published in the GitHub repository mapbox/mcp-docs-server (1 stars, last pushed 6d ago), licensed MIT. It adds 932 tokens to every session, about $0.0047 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.

Languages Testing Writing and docs

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 · 5,182 tokens

buildNext

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

mcp-docs-server AGENTS.md