Vehicle Intelligence MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PIPELINE_BASE_URL | No | Alternative environment variable for the pipeline API base URL. | http://localhost:8000 |
| VEHICLE_MCP_HTTP_HOST | No | Streamable HTTP bind host. | 127.0.0.1 |
| VEHICLE_MCP_HTTP_PORT | No | Streamable HTTP bind port. | 8080 |
| VEHICLE_MCP_TRANSPORT | No | Select stdio or http. | stdio |
| VEHICLE_MCP_MAX_ATTEMPTS | No | Maximum attempts for transient reads. Valid range: 1 through 5. | 3 |
| VEHICLE_MCP_POOL_TIMEOUT | No | Connection-pool timeout in seconds. | 2.0 |
| VEHICLE_MCP_READ_TIMEOUT | No | Pipeline read timeout in seconds. | 10.0 |
| VEHICLE_MCP_WRITE_TIMEOUT | No | Pipeline write timeout in seconds. | 5.0 |
| VEHICLE_MCP_CONNECT_TIMEOUT | No | Pipeline connection timeout in seconds. | 2.0 |
| VEHICLE_MCP_PIPELINE_BASE_URL | No | Pipeline API base URL. PIPELINE_BASE_URL is also accepted. | http://localhost:8000 |
| VEHICLE_MCP_MAX_RESPONSE_BYTES | No | Maximum pipeline response size. Valid range: 10 KiB through 10 MiB. | 1048576 |
| VEHICLE_MCP_ALLOW_INSECURE_BIND | No | Permit a non-loopback bind for a controlled container network. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_vehiclesB | List a bounded page of canonical vehicle summaries from the catalog for discovery. |
| lookup_vehicleA | Retrieve the current canonical record and audit metadata for one validated VIN. |
| explain_vehicle_fieldB | Explain one vehicle field outcome (RESOLVED, UNRESOLVED, or ABSENT) using current evidence. |
| get_vehicle_historyB | Retrieve historical canonical revisions for a vehicle in newest-first order. |
| get_vehicle_revisionA | Retrieve one exact immutable canonical revision for a vehicle by revision number. |
| get_source_observationA | Retrieve one exact immutable source observation by ID, including verified raw payload. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a distinct role: browsing, current lookup, revision history, exact revision, raw observation, and field explanation. The closest pair is lookup_vehicle and get_vehicle_revision, but their current-vs-immutable distinction is clear from descriptions.
Names follow a mostly consistent verb_noun snake_case pattern with list_* for collections and get_* for individual records. lookup_vehicle breaks the get_* convention slightly, but it is still readable and predictable.
Six tools is well within the ideal range and each tool addresses a distinct part of vehicle intelligence. The set feels neither thin nor bloated.
The read-only workflow is well covered: discover vehicles, retrieve current and historical canonical states, fetch raw evidence, and explain field outcomes. A minor gap is the lack of a way to enumerate source observations for a vehicle directly rather than by known observation ID.