Live 85 Actions

OpenStreetMap MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne OpenStreetMap MCP server support?

The StackOne OpenStreetMap MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Connect your AI agent to StackOne's OpenStreetMap MCP server and give it 85 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

OpenStreetMap MCP Server

Built by

StackOne

Coverage

85 Agent Actions

Create, read, update, and delete across OpenStreetMap — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your OpenStreetMap MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every OpenStreetMap tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every OpenStreetMap call.

Tools Discovery →

What is the OpenStreetMap MCP Server?

A OpenStreetMap MCP server lets AI agents read and write OpenStreetMap data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's OpenStreetMap MCP server ships with 85 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All OpenStreetMap MCP Tools

Every action from OpenStreetMap's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Changesets

Create Changeset
Open a new changeset (returns its ID)
Upload Changeset
Upload an OsmChange diff to a changeset atomically (all-or-nothing)
Get Changeset
Read a changeset's metadata (optionally with discussion)
Download Changeset
Download the changes in a changeset as an OsmChange document
List Changesets
Query changesets by bbox, user, time, and open/closed state
Update Changeset
Update the tags of an open changeset

Nodes

Create Node
Create a new node in an open changeset
Get Node
Read the current version of a node
Get Nodes
Multi-fetch nodes by ID list
Update Node
Update a node (optimistic-lock on version)
Delete Node
Delete a node

Ways

Create Way
Create a new way (references node IDs, max 2000)
Get Way
Read the current version of a way
Get Ways
Multi-fetch ways by ID list
Update Way
Update a way (optimistic-lock on version)
Delete Way
Delete a way

Relations

Create Relation
Create a new relation (references member elements)
Get Relation
Read the current version of a relation
Get Relations
Multi-fetch relations by ID list
Update Relation
Update a relation (optimistic-lock on version)
Delete Relation
Delete a relation

Gpx Traces

Create Gpx Trace
Upload a new GPX trace file
Update Gpx Trace
Update a GPS trace's metadata (owner only)
Delete Gpx Trace
Delete a GPS trace (owner only)

Users

Get User
Read a user's public profile by numeric ID
Get Users
Multi-fetch user details by ID list

User Preferences

Get User Preferences
Read all of the authenticated user's preferences
Get User Preference
Read a single preference value by key
Delete User Preference
Delete a single preference by key

Notes

Create Note
Create a new map note (anonymous allowed; write_notes if authenticated)
List Notes
Fetch map notes within a bounding box
Get Note
Read a single note and its comment thread
Search Notes
Search notes by text, author, and date

Messages

Send Message
Send a private message to another user
Get Message
Read a single private message (marks it read)
Delete Message
Delete a private message

Other (49)

Get Api Versions
List API versions supported by the server
Get Capabilities
Get server capabilities and limits (max bbox, changeset element cap, timeouts)
Get Permissions
List OAuth permissions granted to the current token
Get Map Data
Fetch all nodes/ways/relations within a bounding box
Get Node History
Fetch all versions of a node
Get Node Version
Fetch a specific version of a node
Get Node Relations
List relations that reference this node
Get Node Ways
List ways that use this node
Get Way History
Fetch all versions of a way
Get Way Version
Fetch a specific version of a way
Get Way Relations
List relations that reference this way
Get Way Full
Fetch a way plus all its member nodes
Get Relation History
Fetch all versions of a relation
Get Relation Version
Fetch a specific version of a relation
Get Relation Relations
List relations that reference this relation
Get Relation Full
Fetch a relation plus all referenced members
Get Trackpoints
Fetch raw public GPS trackpoints within a bounding box (paged, 5000/page)
Get Gpx Trace Details
Read a GPS trace's metadata
Get Gpx Trace Data
Download the raw GPS trace data file
List Own Gpx Traces
List the authenticated user's own GPS traces
Get Current User
Read the authenticated user's own profile details
Get Notes Feed
RSS feed of note activity (optionally by bbox)
List Inbox Messages
List the authenticated user's received private messages
List Outbox Messages
List the authenticated user's sent private messages
Get Place Details
Show full internal details of a single place
Update Message Status
Update a message's read/unread flag
Close Changeset
Close an open changeset
Comment Changeset
Add a comment to a closed changeset's discussion
Subscribe Changeset
Subscribe to a changeset's discussion notifications
Unsubscribe Changeset
Unsubscribe from a changeset's discussion
Unhide Changeset Comment
Unhide a previously hidden changeset comment (moderator)
Hide Changeset Comment
Hide a changeset comment (moderator)
Redact Node Version
Redact/un-redact a node version (moderator)
Redact Way Version
Redact/un-redact a way version (moderator)
Redact Relation Version
Redact/un-redact a relation version (moderator)
Replace User Preferences
Replace the authenticated user's entire preference set
Comment Note
Add a comment to an open note (auth required)
Close Note
Close (resolve) a note
Reopen Note
Reopen a closed note
Subscribe Note
Subscribe to a note's updates
Unsubscribe Note
Unsubscribe from a note's updates
Hide Note
Hide (delete) a note (moderator)
Geocode Search
Forward geocode: find places by free-form or structured address/name
Reverse Geocode
Reverse geocode: build an address from a lat/lon coordinate
Lookup Osm Objects
Look up address details for known OSM objects by ID
Nominatim Status
Report whether the Nominatim service/database is up
Run Overpass Query
Execute an Overpass QL query and return matching OSM data
Overpass Status
Report current rate-limit slots and quota for the caller's IP
Kill Overpass Queries
Terminate the caller's currently running Overpass queries

Set Up Your OpenStreetMap MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to OpenStreetMap in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

OpenStreetMap MCP Server FAQ

Does StackOne have a OpenStreetMap MCP server?

Yes. StackOne offers a hosted OpenStreetMap MCP server with 85 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.

OpenStreetMap MCP server vs direct API integration — what's the difference?

A OpenStreetMap MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling OpenStreetMap. A OpenStreetMap MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling OpenStreetMap at runtime. StackOne provides both.

How does OpenStreetMap authentication work for AI agents?

OpenStreetMap authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own OpenStreetMap account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are OpenStreetMap MCP tools vulnerable to prompt injection?

Yes — OpenStreetMap MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.

What is the context bloat of a OpenStreetMap agent and how do I avoid it?

Context bloat happens when OpenStreetMap tool schemas and API responses eat your OpenStreetMap agent's memory, preventing it from reasoning effectively. A single OpenStreetMap query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.

Can I limit which actions my OpenStreetMap agent can access?

Yes — you can limit which actions your OpenStreetMap agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.

Can I create custom agent actions for my OpenStreetMap MCP server?

Yes — you can create custom agent actions for your OpenStreetMap MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research OpenStreetMap's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a OpenStreetMap MCP server?

Skip a OpenStreetMap MCP server if your integration is purely software-to-software — direct OpenStreetMap API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call OpenStreetMap actions at runtime.

What AI frameworks and AI clients does the StackOne OpenStreetMap MCP server support?

The StackOne OpenStreetMap MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo

OpenStreetMap MCP Serverfor AI Agents