osmmcp
An MCP (Model Context Protocol) server written in Go that exposes OpenStreetMap-related geospatial tools to LLM/MCP clients. It provides primitives such as geocoding/reverse geocoding, distance calculations, bounding box/centroid utilities, OSM tag-based queries and nearby place search, routing via OSRM (including route directions and sampling), route enrichment (e.g., emissions/cost/calories), and additional domain tools like EV charging station lookup and neighborhood/livability-style analysis.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
The README emphasizes security-related engineering practices (HTTP clients with timeouts/connection limits, structured logging, context cancellation). However, no authentication/authorization for the MCP server is described, which means any access control must be handled externally (network/process permissions). TLS is not explicitly described (stdin/stdout MCP server suggests local transport), but upstream HTTP likely uses HTTPS; exact enforcement is not provided. The tool relies on third-party public geospatial services, so data exposure to those services is inherent to operation.
⚡ Reliability
Best When
You want an agent-friendly, self-hosted MCP toolset that combines OpenStreetMap data querying with routing and additional geospatial enrichment for interactive LLM workflows.
Avoid When
You cannot tolerate reliance on external geospatial services (e.g., OSM/Nominatim/Overpass/OSRM) or you require robust access control, strong security guarantees around data flows, or a documented reliability/SLA.
Use Cases
- • LLM-assisted geocoding (address/place name to coordinates) and reverse geocoding
- • Finding nearby points of interest by category within a radius and/or bounding box
- • OSM tag filtering and distance-based sorting of OSM elements
- • Route planning and route analysis (routing, directions, sampling polyline points)
- • EV charging station discovery near a location or along a route
- • Meeting point suggestion for multiple participants
- • Neighborhood/commute-style analyses using location inputs
Not For
- • Production systems that require authenticated access control or user-based authorization at the MCP layer (none is described)
- • Applications needing a guaranteed SLA or explicit uptime commitments from the provider (the server is self-hosted and no SLA is documented)
- • Use cases requiring first-party data residency or regulated compliance guarantees from the package itself (relies on third-party services)
- • High-throughput workloads without careful rate-limit tuning (explicit rate-limit knobs are mentioned)
Interface
Authentication
No authentication mechanism for the MCP server itself is described in the provided README. The server runs locally and communicates with upstream public geospatial services; those upstream services may enforce their own rate limits.
Pricing
No pricing model is described; it appears to be a self-hosted open-source tool. Costs may come indirectly from upstream service usage and infrastructure hosting.
Agent Metadata
Known Gotchas
- ⚠ Upstream rate limits apply (Nominatim/Overpass/OSRM). The README mentions configurable rps/burst, but agents may still need backoff/retry strategies.
- ⚠ Some tools accept bounding boxes/radii/limits; overly broad parameters can cause large upstream queries and slow responses.
- ⚠ Because it depends on external services for OSM data and routing, transient upstream failures can occur; no explicit retry/backoff guidance is shown in the provided excerpt.
- ⚠ The MCP server appears to run over stdin/stdout for MCP requests; some MCP clients require exact process configuration.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for osmmcp.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.