Context Engine MCP
by cybernuki
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP server listen port. | 8080 |
| QDRANT_URL | No | Qdrant cluster endpoint. | |
| REPO_ROOTS | No | Required for HTTP mode. JSON object `repoId -> absolute path`, e.g. `{"my-app@main":"/repos/main","my-app@development":"/repos/dev"}`. | |
| DEFAULT_TOP_K | No | Default search result count. | 10 |
| EMBED_THREADS | No | ONNX intra-op threads for embedding. | 1 |
| MAX_FILE_SIZE | No | Max file size to index (bytes). | 1048576 |
| MCP_TRANSPORT | No | Set to `http` to enable Streamable HTTP transport (default: stdio). | stdio |
| MCP_AUTH_TOKEN | No | Required for HTTP mode. Every `/mcp` request needs `Authorization: Bearer <token>` (constant-time compare). Server refuses to start if unset. | |
| QDRANT_API_KEY | No | Qdrant API key (if auth enabled). | |
| REPOS_REGISTRY | No | Path to a repo registry JSON (`deploy/repos.example.json` shape: `repos[]` with `name`, `project`, `branches.base`, `branches.head` or null). Unset or missing file: behave as without a registry. | |
| EMBEDDING_MODEL | No | Embedding model name. | BAAI/bge-small-en-v1.5 |
| EMBED_BATCH_SIZE | No | Chunks per embedding call. | 32 |
| INDEX_FILE_BATCH | No | Files per indexing group (chunk, embed/reuse, upsert, save state). | 25 |
| VECTOR_DIMENSION | No | Vector dimension (must match model). | 384 |
| EMBEDDING_CACHE_DIR | No | Fastembed model cache directory (Docker: `/data/fastembed-cache`, mount a volume). | |
| ALLOW_REMOTE_FULL_INDEX | No | Set to `true` to allow `mode: "full"` over HTTP (default: disabled). | false |
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