Waggle MCP Server

Persistent graph-backed conversational memory for AI agents.

Remote serverstreamable-httpPython

What is the Waggle MCP server?

Waggle MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Persistent graph-backed conversational memory for AI agents.

What you get

Persistent memory that remembers decisions, reasons, and contradictions across sessions.

What the assistant can call

Once Waggle is connected, these are the calls the assistant has available:

  • observe_conversation — After any turn containing a decision, preference, constraint, correction, or project fact. Persists the verbatim turn first, then extracts graph
  • query_graph — Before answering questions that may depend on prior context. Hybrid retrieval (graph + verbatim transcript) by default. Supports as_of for
  • prime_context — At the start of a new session to hydrate context from the most relevant scoped memories
  • graph_diff — When the user asks what changed recently
  • update_node — Update an existing node's content, label, or tags
  • delete_node — Delete a node and all its edges
  • decompose_and_store — Break long content into atomic nodes and infer edges automatically
  • dedup_candidates — Return near-duplicate node pairs above a similarity threshold for human review
  • canonicalize_node — Merge multiple nodes into one canonical node. Repoints all edges, collects aliases. Idempotent
  • edge_quality_report — Audit edge quality — counts, average confidence per type, top/bottom confidence edges
  • debug_retrieval — Diagnose retrieval ranking for a query — embedding scores, window routing, tiered vs flat comparison
  • Codex — Waggle is available for Codex as a self-hosted local MCP plugin. No hosted backend, Apple Developer ID, or Windows Authenticode certificate is

Configuration and credentials

You will need 6 environment variables: WAGGLE_TRANSPORT, WAGGLE_BACKEND, WAGGLE_DB_PATH, WAGGLE_DEFAULT_TENANT_ID, WAGGLE_MODEL, WAGGLE_STARTUP_MODE. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Choosing this one

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Waggle's toolset — observe_conversation, query_graph, prime_context and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Abhigyan-Shekhar; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Waggle.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the waggle mcp server does with a few real requests.

Available tools

ToolWhat it does
observe_conversationAfter any turn containing a decision, preference, constraint, correction, or project fact. Persists the verbatim turn first, then extracts graph nodes. Returns turn_id, verbatim_stored, nodes_extracted, edges_inferred.
query_graphBefore answering questions that may depend on prior context. Hybrid retrieval (graph + verbatim transcript) by default. Supports as_of for point-in-time queries.
prime_contextAt the start of a new session to hydrate context from the most relevant scoped memories.
graph_diffWhen the user asks what changed recently.
update_nodeUpdate an existing node's content, label, or tags.
delete_nodeDelete a node and all its edges.
decompose_and_storeBreak long content into atomic nodes and infer edges automatically.
dedup_candidatesReturn near-duplicate node pairs above a similarity threshold for human review.
canonicalize_nodeMerge multiple nodes into one canonical node. Repoints all edges, collects aliases. Idempotent.
edge_quality_reportAudit edge quality — counts, average confidence per type, top/bottom confidence edges.
debug_retrievalDiagnose retrieval ranking for a query — embedding scores, window routing, tiered vs flat comparison.
CodexWaggle is available for Codex as a self-hosted local MCP plugin. No hosted backend, Apple Developer ID, or Windows Authenticode certificate is required: users download the marketplace zip from GitHub Releases, add it to
CursorCursor Settings → Features → MCP Servers → + Add - Command: waggle-mcp - Args: serve - Env vars: same keys as the JSON block above.
AntigravityThe AI agent reads ~/.gemini/antigravity/mcp_config.json (macOS/Linux) or %USERPROFILE%\.gemini\antigravity\mcp_config.json (Windows). Add the waggle block there. The VS Code extension panel reads a different file — addi

How to install the Waggle MCP server

{
  "mcpServers": {
    "waggle": {
      "command": "waggle-mcp",
      "args": ["serve"],
      "env": {
        "WAGGLE_TRANSPORT": "stdio",
        "WAGGLE_BACKEND": "sqlite",
        "WAGGLE_DB_PATH": "~/.waggle/waggle.db",
        "WAGGLE_DEFAULT_TENANT_ID": "local-default",
        "WAGGLE_MODEL": "all-MiniLM-L6-v2",
        "WAGGLE_STARTUP_MODE": "normal"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
WAGGLE_TRANSPORTConfiguration value read at startup.Optional
WAGGLE_BACKENDConfiguration value read at startup.Optional
WAGGLE_DB_PATHFilesystem location the server is allowed to use.Optional
WAGGLE_DEFAULT_TENANT_IDConfiguration value read at startup.Optional
WAGGLE_MODELConfiguration value read at startup.Optional
WAGGLE_STARTUP_MODEConfiguration value read at startup.Optional

Example prompts to try

  • Use Waggle to observe conversation.
  • Use Waggle to query graph.
  • Use Waggle to prime context.

Frequently asked questions

It connects Waggle to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (observe_conversation, query_graph, prime_context, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Waggle directly.