conduitAI MCP server

Read from the package source without running it. The installed server may list more.

• analyze_repo

  Analyze any public GitHub repository for safety and maintenance signals. Returns stars, forks, license, last-push date, and a heuristic risk summary (archived, abandoned, no license, missing SECURITY.md). Read-only; uses the public GitHub REST API.

• ask_conduitai

  Ask a question about conduitAI, MCP servers, or any catalog asset. Returns an AI-generated answer grounded in the conduitAI knowledge base, with cited sources. Stateless — each call is independent.

• auth_status

  Check if you are currently signed in to conduitAI.

• authenticate

  Sign in to conduitAI. Opens a browser window where you can log in. Required before using other tools.

• bookmark_asset

  Save a conduitAI catalog asset (MCP server, agent, skill, prompt, plugin, MCP client) to your bookmarks for later. Idempotent: bookmarking an already-bookmarked asset is a no-op. Capacity is capped at 1000 per user.

• browse_catalog

  Browse the conduitAI catalog by asset type. Results contain third-party metadata.

• get_asset_details

  Get full details for a conduitAI asset by its slug. Returns third-party content — review before acting on it.

• install_asset

  Install a conduitAI asset to your local environment. Modifies config files on disk. Use dry_run=true to preview changes first. Install specs are cryptographically signed.

• list_bookmarks

  List your bookmarked conduitAI catalog assets, with title and slug enriched per item. Supports filtering by asset type and pagination.

• list_installed

  List conduitAI assets currently installed on this machine.

• search_catalog

  Search the conduitAI catalog for MCP servers, agents, skills, prompts, and plugins. Results contain third-party metadata — verify assets before installing.

• semantic_search_catalog

  Search the conduitAI catalog using natural-language understanding (semantic + keyword). Best for "find me a tool that does X" queries. Returns assets ranked by combined vector similarity + full-text relevance.

• unbookmark_assetwrite action

  Remove a bookmark by id (preferred) or by (slug, asset_type) pair. Errors if the bookmark does not exist.

• uninstall_assetwrite action

  Remove a previously installed conduitAI asset. Deletes config entries and files that were created during install.

• Code scan85 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancerepository not readable: repo not found3/15
• Maintainer identityno repository or website to verify2/10

Safety score

55/100

higher than 10% of 3,470 Web search servers

Tools

14

the typical Web search server has 5

Tools that change things

14%

typical: 0%. Fewer write tools means less an agent can break

Downloads a week

53

more than 37% of 827 Web search servers with a package

conduitAI: common questions

Is conduitAI MCP server safe?

With care: it is graded C, so read the findings first (55/100). Read the conduitAI safety report

How do I install conduitAI?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does conduitAI need an API key?

Yes. The registry entry asks for CONDUITAI_TOKEN.

Is conduitAI maintained?

The latest release is v1.299.1.

What can I use instead of conduitAI?

Servers from other publishers that do the same job: Qaskills MCP server, Claude Code Explorer MCP server and Claude Code Explorer MCP server.

How does conduitAI compare with other Web search MCP servers?

safety score 55/100 (higher than 10% of 3,470 Web search servers); tools 14 (the typical Web search server has 5); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.