How do I connect Waggle MCP Server to Claude?

The listing records `claude mcp add --transport stdio waggle -- waggle-mcp serve --transport stdio` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Desktop, Claude Code, Cursor as compatible clients.

Is Waggle MCP Server free?

The listed licence is Apache-2.0. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.

What can Waggle MCP Server do?

Waggle MCP Server documents 39 tools to the agent, including aggregate_graph, apply_approved_memory_change, canonicalize_node. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.

Waggle MCP

Unclaimed

by Abhigyan-Shekhar

MCP server for external memory layer for AI agents + more . Download from pypi , and get started

Install

$claude mcp add --transport stdio waggle -- waggle-mcp serve --transport stdio

Set up this server

Compare servers My Stack

This server needs project-specific setup. Follow the project instructions; no reusable public launch command is available yet.

Project instructions

agent-memoryai-agentsgraph-memoryknowledge-graphllm-memorymcpmcp-serverpython

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

39 of 39 tools

Documented tools (39)

From project documentation. A server handshake does not verify each tool’s description or behavior.

aggregate_graph

Broad filtered subgraph for map-reduce tasks. Use when you want a large scoped slice rather than high-precision top-K. Supports nodetypes, tags, asof, includeinvalidated.

apply_approved_memory_change

Applies the exact approved value using only a proposal ID.

canonicalize_node

Merge multiple nodes into one canonical node. Repoints all edges, collects aliases. Idempotent.

close_context_window

Close a session window and derive cross-window edges.

debug_retrieval

Diagnose retrieval ranking for a query — embedding scores, window routing, tiered vs flat comparison.

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.

delete_node

Delete a node and all its edges.

diff

git diff

edge_quality_report

Audit edge quality — counts, average confidence per type, top/bottom confidence edges.

export_graph_html

Export the memory graph as an interactive HTML visualization.

export_markdown_vault

Export the graph as an Obsidian-compatible Markdown vault.

fsck

git fsck

get_context_window

Inspect one context window and its nodes.

get_node_history

Inspect a node's evidence, validity window, and connected context.

get_project_brief

Returns the project's goal, current decisions, constraints, state, and open questions.

get_related

Fetch the neighborhood around a specific node by ID.

get_stats

Node/edge counts, type breakdowns, and recent highly-connected nodes.

get_topics

Topic clusters via community detection across the full tenant graph.

graph_diff

When the user asks what changed recently.

grep

git grep

import_markdown_vault

Import an edited Obsidian vault back into the graph non-destructively.

list_conflicts

List unresolved contradiction and update edges.

list_context_scopes

Known agent, project, and session scope values.

list_context_windows

Chat/session-level memory containers with status and node counts.

load_abhi_chunks

—

load_abhi_for_session

Loads a portable graph into this browser tab and returns a brief.

merge

git merge

observe_conversation

After any turn containing a decision, preference, constraint, correction, or project fact. Persists the verbatim turn first, then extracts graph nodes. Returns turnid, verbatimstored, nodesextracted, edgesinferred.

prime_context

At the start of a new session to hydrate context from the most relevant scoped memories.

propose_memory_change

Creates a pending correction for human review without changing authoritative memory.

pull

git pull

query_graph

Before answering questions that may depend on prior context. Hybrid retrieval (graph + verbatim transcript) by default. Supports asof for point-in-time queries.

recall_memory

Finds current authoritative memories for a query, with supersession provenance when available.

resolve_conflict

Mark a conflict resolved. Pass winner (node ID) to supersede the losing node — sets its validto to now.

show

git show

timeline

Chronological view of memory changes for a node or query.

update_node

Update an existing node's content, label, or tags.

window_graph_viz

Export the context-window graph as an interactive HTML visualization.

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about Waggle MCP Server

How do I connect Waggle MCP Server to Claude?: The listing records `claude mcp add --transport stdio waggle -- waggle-mcp serve --transport stdio` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Desktop, Claude Code, Cursor as compatible clients.
Is Waggle MCP Server free?: The listed licence is Apache-2.0. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can Waggle MCP Server do?: Waggle MCP Server documents 39 tools to the agent, including aggregate_graph, apply_approved_memory_change, canonicalize_node. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.