# Clauderecall Recall MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.clauderecall%2Frecall
Registry id: `mcp-registry/com.clauderecall/recall`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "clauderecall-recall-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@clauderecallhq/cli"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add clauderecall-recall-mcp-server -- npx -y @clauderecallhq/cli
```

## Tools (35)

- `add_session_to_collection`: Idempotent collection membership
- `append_note`: Add markdown to session note; separated by ---
- `apply_tags`: Add tags to a session (merge-mode, never deletes)
- `bucket_expand`: Chunks surrounding a search hit, in original document order
- `bucket_list`: Inventory of local document buckets: names, document/chunk counts, top headings
- `bucket_search`: Hybrid keyword + semantic search inside one bucket; best-matching passages with heading path
- `context_for_session`: Condensed markdown export, ready to inject
- `create_collection`: New collection; optional parent, icon, color
- `doctor`: Read-only health snapshot: db size, WAL, FTS5 fragmentation, integrity check
- `find_similar_sessions`: Semantic similarity via vector embeddings (Pro)
- `generate_thread_titles`: Generate coherent titles for sessions in thread DAG
- `get_session`: Full transcript (accepts 8+ char id prefix)
- `list_projects`: Every indexed project with session/message counts
- `list_sessions`: Recent sessions; filters: project, tag, date range
- `list_sessions_to_tag`: Surface untagged sessions for review (auto-tag flow)
- `list_tags`: Tag cloud with counts, most popular first
- `locate_sessions`: Find history by topic/name/UUID and check live messaging availability (Pro)
- `optimize`: WAL checkpoint, FTS5 segment merge, planner stats refresh; optional VACUUM
- `recall_neighborhood`: Bundle parents/children/citations/similar as one budget-bounded markdown blob
- `remove_session_from_collection`: Remove session; logged in append-only log
- `search`: Full-text search with #tag support; BM25 + optional vector fusion
- `semantic_status`: Health snapshot: embedder model, worker state, queue depth
- `set_alias`: Human-friendly session name; previous alias archived
- `sync_active_sessions`: Capture sessions open in one repo into a single thread
- `thread_add_session`: Attach session; role=origin or child
- `thread_archive`: Soft-delete thread; hidden by default
- `thread_create`: Create thread, optionally seed with origin session
- `thread_for_session`: Non-archived threads referencing a session
- `thread_get`: Full thread detail with every session edge
- `thread_list`: All threads, newest first; can exclude archived
- `thread_merge`: Move all edges from source to dest, delete source
- `thread_remove_session`: Detach session from thread
- `thread_rename`: Change thread display name
- `thread_set_parent`: Change parent within thread; null clears parent
- `thread_split`: Peel sessions into new thread

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.