Is io.github.Abhigyan-Shekhar/Waggle-mcp safe to use?

io.github.Abhigyan-Shekhar/Waggle-mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.Abhigyan-Shekhar/Waggle-mcp?

io.github.Abhigyan-Shekhar/Waggle-mcp can be installed by cloning its GitHub repository and following the setup instructions in the README.

What AI clients work with io.github.Abhigyan-Shekhar/Waggle-mcp?

io.github.Abhigyan-Shekhar/Waggle-mcp is compatible with Claude Desktop, Cursor, Claude Code, and most MCP clients that support stdio transport. It uses stdio transport.

io.github.Abhigyan-Shekhar/Waggle-mcp

Persistent graph-backed conversational memory for AI agents.

0 tools GitHub

No known CVEs

No license

Maintenance unknown

No commit data

Untested

Transport: stdio

0 tools

Grade F

AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Untested on Claude Desktopstdio · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "io-github-abhigyan-shekhar-waggle-mcp": {
      "command": "<see-readme>",
      "args": []
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-abhigyan-shekhar-waggle-mcp)](https://mcppedia.org/s/io-github-abhigyan-shekhar-waggle-mcp)

Read me

What io.github.Abhigyan-Shekhar/Waggle-mcp does

Persistent graph-backed conversational memory for AI agents.

Test This Server

No automated test available for this server. Check the GitHub README for setup instructions.

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

15/100across 5 weighted dimensions

How we score →

0255075100

−85

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

No package registry to scan.

Help improve this page

This server is missing a description. Tools and install config are also missing.If you've used it, help the community.

Add information

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.Abhigyan-Shekhar/Waggle-mcp safe to use?: io.github.Abhigyan-Shekhar/Waggle-mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.Abhigyan-Shekhar/Waggle-mcp?: io.github.Abhigyan-Shekhar/Waggle-mcp can be installed by cloning its GitHub repository and following the setup instructions in the README.
What AI clients work with io.github.Abhigyan-Shekhar/Waggle-mcp?: io.github.Abhigyan-Shekhar/Waggle-mcp is compatible with Claude Desktop, Cursor, Claude Code, and most MCP clients that support stdio transport. It uses stdio transport.

Similar servers

Others in ai-ml

View all →

Sequential Thinking MCP Server98

Dynamic problem-solving through sequential thought chains

84.3k 1

XcodeBuildMCP96

A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

5.3k 2

Gemini Cli95

An open-source AI agent that brings the power of Gemini directly into your terminal.

102.1k 8

Python Sdk95

The official Python SDK for Model Context Protocol servers and clients

22.7k 1

MCP Security Weekly

Get CVE alerts and security updates for io.github.Abhigyan-Shekhar/Waggle-mcp and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Untested on Claude Desktopstdio · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "io-github-abhigyan-shekhar-waggle-mcp": {
      "command": "<see-readme>",
      "args": []
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-abhigyan-shekhar-waggle-mcp)](https://mcppedia.org/s/io-github-abhigyan-shekhar-waggle-mcp)

Read me

What io.github.Abhigyan-Shekhar/Waggle-mcp does

Persistent graph-backed conversational memory for AI agents.

Test This Server

No automated test available for this server. Check the GitHub README for setup instructions.

README

Your AI forgets everything between sessions. Waggle gives it a graph-backed brain.
Persistent, structured memory for AI agents — typically lower-token than chunk-based retrieval, often 2-4× on factual lookups.

Waggle is not a code indexer. It's a conversational memory engine — it remembers what you decided, why, and what changed, across every session.

What's New — v0.1.9

Rollover transcript handoff CLI: waggle-mcp ingest-transcript-handoff ingests full ordered transcripts, deduplicates them with message_identity, and exports a session-scoped handoff bundle for the next window or IDE.
Cross-run completion fixes: append-only reruns now avoid reprocessing already completed turns while still completing a previously trailing user block when the matching assistant arrives later.
Evidence alignment fixes: batch-ingested nodes now keep evidence turn indices aligned with the actual stored transcript rows, including tool/system-interleaved sessions.
Export error contract hardening: handoff export failures now surface as real CLI failures instead of being silently downgraded into export_skipped.
Benchmark harness: end-to-end WaggleAdapter connecting the graph engine to ConvoMem / MemBench runners with automated exact-match scoring and latency logging.
LongMemEval integration: CLI-driven retrieval evaluation against the official LongMemEval split (97.4% R@5 / 88.2% Exact@5 in graph_raw, 96.4% / 85.6% in graph_hybrid).
Observability stack: Grafana dashboard, Prometheus config, and Docker Compose overlay in deploy/observability/.
Operational runbooks: incident response, secret management, API-key rotation, and onboarding guides added to docs/runbooks/.

Who is this for?

→ Individual developer extending Claude, Codex, Cursor, or Antigravity with persistent memory: Use Python 3.11+ and install via pipx (no venv activation needed): brew install pipx && pipx ensurepath && pipx install waggle-mcp && waggle-mcp init. SQLite + local embeddings, zero infra.

→ Team running a shared memory service: Waggle ships with a Docker image, Kubernetes manifests, Prometheus metrics, and multi-tenant auth. See deploy/kubernetes/ and docs/runbooks/.

Both paths share the same MCP tool surface — the difference is only the backend and transport.

Why waggle-mcp?

waggle-mcp is a local-first memory layer for MCP-compatible AI clients, built on a persistent knowledge graph.

Stuffed context	Structured retrieval
Huge prompts every session	Compact subgraph retrieved at query time
Session-local memory	Persistent multi-session memory
F

... View full README on GitHub

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

15/100across 5 weighted dimensions

How we score →

0255075100

−85

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

No package registry to scan.

Help improve this page

This server is missing a description. Tools and install config are also missing.If you've used it, help the community.

Add information

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.Abhigyan-Shekhar/Waggle-mcp safe to use?: io.github.Abhigyan-Shekhar/Waggle-mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.Abhigyan-Shekhar/Waggle-mcp?: io.github.Abhigyan-Shekhar/Waggle-mcp can be installed by cloning its GitHub repository and following the setup instructions in the README.
What AI clients work with io.github.Abhigyan-Shekhar/Waggle-mcp?: io.github.Abhigyan-Shekhar/Waggle-mcp is compatible with Claude Desktop, Cursor, Claude Code, and most MCP clients that support stdio transport. It uses stdio transport.