MIRAI Intelligence & Research MCP
by Tarant336
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MIRAI_CONFIG | No | Optional path to a mirai.config.json configuration file. | |
| MIRAI_DATA_DIR | No | Knowledge base storage location. | ~/.mirai-mcp |
| MIRAI_LAB_TOKEN | No | Required token for active lab testing. | |
| MIRAI_LOG_LEVEL | No | Log level: debug, info, warn, or error. | info |
| MIRAI_TRANSPORT | No | Transport mode; stdio (HTTP not enabled). | stdio |
| MIRAI_WORKSPACE | No | Directory boundary for reads/writes. | process.cwd() |
| MIRAI_EXEC_TIMEOUT_MS | No | Hard timeout per sandboxed command, in milliseconds. | 120000 |
| MIRAI_ALLOW_PUBLIC_FETCH | No | Allow public network access (read-only). | true |
| MIRAI_MAX_ARTIFACT_BYTES | No | Cap for artifacts read into memory, in bytes. | 268435456 |
| MIRAI_ALLOW_ISOLATED_EXEC | No | Allow command execution inside the isolated sandbox. | true |
| MIRAI_EXEC_MAX_OUTPUT_BYTES | No | Output size cap in bytes. | 4194304 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues