lava-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LAVA_URL | No | LAVA base URL (stdio fallback; HTTP clients send X-Lava-Url) | |
| LAVA_TOKEN | No | API token (stdio fallback; HTTP clients send X-Lava-Token) | |
| LAVA_MCP_HOST | No | HTTP bind host (hosted mode) | |
| LAVA_MCP_PORT | No | HTTP bind port (hosted mode) | |
| LAVA_API_VERSION | No | REST version | v0.3 |
| LAVA_MCP_READ_ONLY | No | Hide write tools (set to 'true' to enable read-only mode) | |
| LAVA_MCP_TRANSPORT | No | Transport type: 'stdio' or 'streamable-http' | stdio |
| LAVA_MCP_GATEWAY_PORT | No | SSH gateway port | 2222 |
| LAVA_MCP_GATEWAY_ENABLED | No | Enable interactive SSH board-session gateway (set to 'true' to enable) | |
| LAVA_MCP_GATEWAY_ADVERTISE_HOST | No | Host containers dial back to |
Capabilities
Features and capabilities supported by this server
| 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 |
|---|---|
| whoamiA | Return the LAVA user your token authenticates as. |
| versionA | Return the version of the connected LAVA server. |
| list_devicesA | List devices, optionally filtered by device_type, health or state. Returns {count, results}. health is e.g. Good/Bad/Maintenance/Unknown; state is Idle/Reserved/Running. |
| get_deviceB | Get the full record for one device by hostname. |
| get_device_dictionaryC | Get a device's rendered configuration dictionary (Jinja2/YAML text). |
| get_qdl_infoA | Summarise a device's QDL/flash capability (qdl/fastboot deploy + boot params). Useful before flashing a Qualcomm board: reports whether the device supports qdl, the qdl deploy/boot method parameters, and all available deploy/boot methods, derived from the device's rendered configuration. |
| list_device_typesC | List the device types known to this LAVA instance. |
| list_workersA | List the dispatcher workers and their health/state. |
| list_jobsB | List test jobs, newest first, with optional filters. state is e.g. Submitted/Scheduling/Scheduled/Running/Canceling/Finished; health is Unknown/Complete/Incomplete/Canceled. |
| get_jobA | Get the full record (state, health, device, times) for one job. |
| get_job_definitionA | Get the original submitted YAML job definition for a job. |
| get_job_logsA | Get a job's logs (YAML). Optionally limit to the [start, end) line range. |
| get_job_resultsC | Get a job's test-case results (pass/fail per case). |
| get_queueB | Get the queue of submitted jobs waiting for a device. |
| get_runningB | Get per-device-type running/reserved counts. |
| get_lab_healthB | Get per-device health across the lab. |
| validate_jobB | Validate a YAML job definition without submitting it. |
| submit_jobC | Submit a YAML job definition. Returns the new job id(s). |
| cancel_jobB | Request cancellation of a running or queued job. |
| resubmit_jobC | Resubmit a finished job with the same definition. |
| set_job_priorityB | Set a job's queue priority (0-100, higher runs sooner). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| devices_resource | The current device inventory. |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mattface/lava-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server