Kaede Recall MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KAEDE_DEDUPE | No | Skip a write when the same content and metadata already exist. | true |
| KAEDE_RETRIES | No | Attempts for a call that fails on a transient connection error. | 3 |
| COLLECTION_NAME | Yes | Name of the default collection to use. | |
| EMBEDDING_MODEL | No | Name of the embedding model to use. | sentence-transformers/all-MiniLM-L6-v2 |
| KAEDE_READ_ONLY | No | Enable read-only mode (disables mutation tools). | false |
| FASTMCP_LOG_LEVEL | No | Set logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL). | INFO |
| KAEDE_BACKEND_URL | No | URL of the vector backend. | |
| EMBEDDING_PROVIDER | No | Embedding provider to use (currently only "fastembed" is supported). | fastembed |
| KAEDE_BACKEND_PATH | No | Path to the local vector database (alternative to KAEDE_BACKEND_URL). | |
| KAEDE_SEARCH_LIMIT | No | Maximum number of results to return from search. | 10 |
| FASTMCP_SERVER_HOST | No | Host address to bind the server to. | 127.0.0.1 |
| FASTMCP_SERVER_PORT | No | Port to run the server on. | 8000 |
| MEMORY_OS_EMBED_URL | No | Memory OS daemon used for embeddings and invalidation. | http://127.0.0.1:7451 |
| FASTMCP_SERVER_DEBUG | No | Enable debug mode. | false |
| KAEDE_BACKEND_API_KEY | No | API key for the vector backend. | |
| MEMORY_OS_EMBED_REMOTE | No | Ask the daemon before loading a local model (false forces local). | true |
| FASTMCP_SERVER_DEPENDENCIES | No | List of dependencies to install in the server environment. | [] |
| FASTMCP_SERVER_ON_DUPLICATE_TOOLS | No | Behavior for duplicate tools (warn, error, replace, ignore). | warn |
| FASTMCP_SERVER_ON_DUPLICATE_PROMPTS | No | Behavior for duplicate prompts (warn, error, replace, ignore). | warn |
| FASTMCP_SERVER_ON_DUPLICATE_RESOURCES | No | Behavior for duplicate resources (warn, error, replace, ignore). | warn |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| memory-recallB | Search long-term memory (facts, decisions, problems, procedures) with a hard size budget. |
| memory-writeA | Store one durable memory. Dedupes, links and supersedes in one call. |
| memory-updateA | Edit a stored memory in place: text, summary, tags or entities. Re-embeds when the trigger or the body changes. |
| memory-deleteA | Delete a memory by exact id or by semantic match, with a dry-run preview. The only way to remove a node. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool maps to a distinct lifecycle action on a single resource: memory-write stores, memory-recall searches, memory-update edits in place, memory-delete removes. The write/update boundary is the only potential source of confusion, but the descriptions clearly separate storing a new memory from editing an existing one.
All four names follow a strict memory-<verb> kebab-case pattern with action-oriented verbs (write, recall, update, delete). Fully predictable and readable.
Four tools cover the full memory lifecycle (create, read/search, update, delete) with no filler. The surface is tightly scoped to the server's single purpose.
Core CRUD lifecycle is fully covered, including a dry-run preview on delete. Minor gaps: no explicit get-by-id or list/browse operation, and no tools for inspecting tags, entities, or links outside of recall results.