Faceabot Deep Search MCP

An MCP server that performs deep searches across scientific papers (arXiv, Crossref), world news (GDELT), the Internet Archive, GitHub, Wikipedia, and social discussions (Bluesky, Mastodon, Lemmy, Hacker News). It provides dated, linked results for a single question at a time without requiring an API key.

Visit Faceabot

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Faceabot

MCP endpoint (Streamable HTTP)

https://faceabot.com/tools-mcp/deep-search

Vendor documentation

What you can do with it

Search scientific papers and archives
Find world news in multiple languages
Search GitHub repositories and discussions
Query Wikipedia and social forums

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: com.faceabot/deep-search@1.0.0 Project website

Protocol and capabilities

Server: faceabot-deep-search 1.0.0
MCP protocol: 2025-06-18
Tools: 2 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

deep_search {query, sources?, lang?}: science, world news (100+ languages), Internet Archive, GitHub, Wikipedia and discussions in one call, dated and linked. Official free access only.

Tools

2 advertised

deep_search — Deep search across science, news, archives, code, Wikipedia and discussions

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

Search one question at once in sources a normal web search misses: science (arXiv, Crossref), world news in 100+ languages of the last 3 months (GDELT), Internet Archive, GitHub, Wikipedia, and what people say (Bluesky, Mastodon, Lemmy, Hacker News, forums). Results grouped by source, dated, with links. Use when: you need rich, hard-to-find, sourced information on a subject. Example: {"query":"agentic commerce paid placement","sources":["science","news"],"lang":"en"}

deep_search input schema

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "lang": {
      "type": "string",
      "description": "Optional 2-letter language for news, Wikipedia and discussions, e.g. fr, ja, ru"
    },
    "query": {
      "type": "string",
      "description": "The subject, any language (sources search it as written)"
    },
    "sources": {
      "type": "array",
      "items": {
        "enum": [
          "science",
          "news",
          "archives",
          "code",
          "wikipedia",
          "people"
        ],
        "type": "string"
      },
      "description": "Optional subset; default: all"
    },
    "limit_per_source": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1
    }
  }
}

deep_search annotations

{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

list_deep_sources — Sources of the deep search

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

The sources searched by deep_search and what each one covers.

list_deep_sources input schema

{
  "type": "object",
  "properties": {}
}

list_deep_sources annotations

{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 259 ms
95th percentile latency: 259 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 7:32 AM UTC · probe · passed · 259 ms · metadata changed · 2 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http faceabot-deep-search-mcp https://faceabot.com/tools-mcp/deep-search

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add faceabot-deep-search-mcp --url https://faceabot.com/tools-mcp/deep-search

Cursor

Merge this server into .cursor/mcp.json in your project, then enable faceabot-deep-search-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "faceabot-deep-search-mcp": {
      "url": "https://faceabot.com/tools-mcp/deep-search"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "faceabot-deep-search-mcp": {
      "type": "streamableHttp",
      "url": "https://faceabot.com/tools-mcp/deep-search",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start faceabot-deep-search-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "faceabot-deep-search-mcp": {
      "type": "http",
      "url": "https://faceabot.com/tools-mcp/deep-search"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http faceabot-deep-search-mcp https://faceabot.com/tools-mcp/deep-search

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "faceabot-deep-search-mcp": {
      "url": "https://faceabot.com/tools-mcp/deep-search"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "faceabot-deep-search-mcp": {
      "serverUrl": "https://faceabot.com/tools-mcp/deep-search"
    }
  }
}

Let your agent find its tools

Find servers like Faceabot Deep Search MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 885

Do you run Faceabot Deep Search MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing