Skip to main content
Glama
MIRAI Intelligence & Research MCP

MIRAI Intelligence & Research MCP

by Tarant336

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MIRAI_CONFIGNoOptional path to a mirai.config.json configuration file.
MIRAI_DATA_DIRNoKnowledge base storage location.~/.mirai-mcp
MIRAI_LAB_TOKENNoRequired token for active lab testing.
MIRAI_LOG_LEVELNoLog level: debug, info, warn, or error.info
MIRAI_TRANSPORTNoTransport mode; stdio (HTTP not enabled).stdio
MIRAI_WORKSPACENoDirectory boundary for reads/writes.process.cwd()
MIRAI_EXEC_TIMEOUT_MSNoHard timeout per sandboxed command, in milliseconds.120000
MIRAI_ALLOW_PUBLIC_FETCHNoAllow public network access (read-only).true
MIRAI_MAX_ARTIFACT_BYTESNoCap for artifacts read into memory, in bytes.268435456
MIRAI_ALLOW_ISOLATED_EXECNoAllow command execution inside the isolated sandbox.true
MIRAI_EXEC_MAX_OUTPUT_BYTESNoOutput 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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources