Implementation Intelligence MCP
by ravishu5
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GH_TOKEN | No | GitHub token commonly used by the GitHub CLI, used as a fallback. | |
| CACHE_PATH | No | Path to the cache SQLite database. | ~/.implementation-mcp/cache.sqlite |
| GITHUB_TOKEN | No | Your GitHub personal access token. Falls back to GITHUB_PERSONAL_ACCESS_TOKEN, GH_TOKEN, `gh auth token`, or unauthenticated. | |
| RANKING_WEIGHTS | No | JSON override for ranking weights; merged over defaults and renormalised. | |
| MAX_REPOSITORIES | No | Maximum number of repositories to consider during discovery. Lowering this materially hurts quality. | 40 |
| ENABLE_CODE_INDEX | No | Whether to enable jCodeMunch for symbol-level analysis. | true |
| MAX_DEEP_ANALYSIS | No | Maximum number of repositories to deeply analyze. | 5 |
| ENABLE_DIAGNOSTICS | No | Attach the metrics block to every result. | false |
| MAX_CONTEXT_TOKENS | No | A ceiling on context tokens, not a target. | 6000 |
| GITHUB_PERSONAL_ACCESS_TOKEN | No | Alternate GitHub personal access token used as a fallback for GITHUB_TOKEN. |
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 issues