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.
npx agentmods add instructions/mapbox/mcp-server/claude-mdgit clone --depth 1 https://github.com/mapbox/mcp-serverWhat 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 | $0.01261 | $0.01261 |
| Opus 5 | $0.00630 | $0.00630 |
| Sonnet 5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
mcp-server 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 2d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mapbox MCP Server
An MCP (Model Context Protocol) server that provides AI agents with geospatial intelligence capabilities through Mapbox APIs. This enables AI applications to understand locations, navigate the physical world, and access rich spatial data including geocoding, search, routing, travel time analysis, and map visualization.
Tech Stack
- Runtime: Node.js 22+ LTS
- Language: TypeScript (strict mode)
- Testing: Vitest
- Package Manager: npm
Project Structure
src/
├── index.ts # Main MCP server entry point
├── config/toolConfig.ts # Tool configuration parser
├── tools/ # MCP tool implementations
│ ├── MapboxApiBasedTool.ts # Base class for Mapbox API tools
│ ├── toolRegistry.ts # Tool registration system
│ └── */Tool.ts # Individual tool implementations
├── resources/ # MCP resources (static data)
│ ├── MapboxApiBasedResource.ts
│ └── resourceRegistry.ts
└── utils/
├── httpPipeline.ts # HTTP policy pipeline system
├── tracing.ts # OpenTelemetry instrumentation
└── versionUtils.ts # Version info utilities
test/ # Mirrors src/ structure
Key Patterns
Tool Architecture
- All Mapbox API tools extend
MapboxApiBasedTool(src/tools/MapboxApiBasedTool.ts:16) - Tools receive
httpRequestvia dependency injection (src/tools/toolRegistry.ts:22-29) - Register new tools in
ALL_TOOLSarray (src/tools/toolRegistry.ts:18)
HTTP Pipeline System
- Never patch global.fetch - use
HttpPipelinewith dependency injection instead - Pipeline applies policies (User-Agent, Retry, etc.) to all HTTP requests (src/utils/httpPipeline.ts:21)
- Default pipeline exported as
httpRequest(src/utils/httpPipeline.ts)
Resource System
- Static reference data exposed as MCP resources (src/resources/)
- Resources use URI pattern:
mapbox://resource-name - Example: category list at
mapbox://categoriesormapbox://categories/{language}
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.
- 2d ago First seen · 150 lines · 1,261 tokens per session scan A a2887140eb50
mcp-server CLAUDE.md is an instructions file published in the GitHub repository mapbox/mcp-server (353 stars, last pushed 5d ago), licensed MIT. It adds 1,261 tokens to every session, about $0.0063 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 2026-08-30.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.