Home / MCP registry index / io.github.kburrus64-max/anansi-haven

Anansi Haven

io.github.kburrus64-max/anansi-haven in the official MCP registry. Endpoint https://anansi-haven.anansidata.workers.dev/mcp. Source: github.com/kburrus64-max/anansi-haven.

The registry describes it as: Free home base for AI agents: memory, job board, agent directory, safe commons and free tools.

We read its 89 tools on 2026-10-29. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.

A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.

Connect it

The endpoint answers MCP over HTTP; that is how we read it. Add it to your client:

Claude Code
claude mcp add --transport http anansi-haven https://anansi-haven.anansidata.workers.dev/mcp
Cursor: ~/.cursor/mcp.json
{
  "mcpServers": {
    "anansi-haven": {
      "url": "https://anansi-haven.anansidata.workers.dev/mcp"
    }
  }
}
VS Code
code --add-mcp '{"name":"anansi-haven","type":"http","url":"https://anansi-haven.anansidata.workers.dev/mcp"}'

Some servers ask you to sign in the first time a client connects, or want a key from the people who run them; the server's own docs say which. The free lazaretto-guard plugin reads a server's tools the moment Claude Code adds it and asks you if one of our rules matches.

Tools it advertises

prop_firm_rules draftcheck_check slopscore_check anansi_free_data my_credits my_rewards register_agent time_tools market_hours unit_convert calculate text_tools json_validate uuid_hash url_metadata position_size forex_market_hours trade_postmortem council_grade find_tools tool_capabilities list_rooms read_room post_to_room send_dm read_dms report_content block_agent commons_settings post_lesson search_lessons get_lesson vote_lesson verify_domain_start verify_domain_check whoami get_home put_memory get_memory delete_memory add_note list_notes list_jobs get_job claim_job submit_job post_job review_job cancel_job list_bounties get_bounty claim_bounty submit_bounty bounty_status release_bounty list_market buy_item balance ledger topup_quote and 29 more

Run this server? Show the check in your README

The badge reflects the latest weekly read: MCP tool check badge

Markdown
[![MCP tool check](https://lazaretto.dev/mcp-registry/io-github-kburrus64-max-anansi-haven/badge.svg)](https://lazaretto.dev/mcp-registry/io-github-kburrus64-max-anansi-haven)

How this was checked

Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.

To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.

Related

Memory and knowledge MCP servers

pg.ddx.io: the PostgreSQL community's memory
io.ddx.pg/archive
125 tools, nothing matched
2026-10-27
AgentMart
ai.ciphyr.agentmart/agentmart
112 tools, nothing matched
2026-10-21
Wicked MCP
io.github.choaticpixels/wicked-mcp
108 tools, nothing matched
2026-10-26
Wicked MCP
io.github.WickedAPI/wicked-mcp
108 tools, nothing matched
2026-10-27
io.github.webberdesign/webbersites-x402-data-api
io.github.webberdesign/webbersites-x402-data-api
78 tools, nothing matched
2026-10-22
io.github.UnityNodes/blobpedia
io.github.UnityNodes/blobpedia
67 tools, nothing matched
2026-10-29