Skip to main content
Glama
hmshuv

closeloop-mcp

by hmshuv

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_MODELNoModel id to use at the LLM endpoint, e.g. openai/gpt-oss-120b or gemini-2.0-flash.
LLM_API_KEYNoAPI key for the OpenAI-compatible LLM endpoint.
CLOSELOOP_DBNoPath to the CloseLoop database that stores state (runs, matches, exceptions, audit, drafts). Defaults to ~/.closeloop/closeloop.db. On first run with an empty database the reproducible demo dataset is seeded automatically.
LLM_BASE_URLNoBase URL of an OpenAI-compatible chat-completions endpoint, e.g. https://api.groq.com/openai/v1. Optional: with no LLM_* variables CloseLoop makes no network requests and every AI step uses its deterministic fallback.
CLOSELOOP_SOURCE_DBNoPath to the customer's source export (a SQLite file in rollback-journal mode, not WAL) attached read-only, e.g. /data/source.db. CloseLoop keeps its own state in a separate database (CLOSELOOP_DB).
LLM_REASONING_EFFORTNoReasoning effort for reasoning models only (e.g. low); keeps answers within the token budget.

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