Integration

Manticore Search integration

Manticore Search is a self-hosted search engine with a JSON over HTTP interface on port 9308. This integration covers that interface: full-text, filtered, faceted, KNN vector and percolate searching, adding, replacing, partially updating and deleting documents one at a time or by match query, autocomplete suggestions with fuzzy matching and keyboard-layout correction, and running arbitrary SQL statements against the daemon. The host is part of the credential because every Manticore install is its own deployment. Authentication is the HTTP basic user name and password the daemon enforces, or a bearer token issued for that user; an instance started without authentication accepts either credential unused.

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Manticore Search.Built from the 9 Manticore Search tools below, on the connection you add once.

Common Manticore Search use cases

  • reading rows with SQL instead of the JSON query DSL
  • creating or altering a table
  • inspecting the tables an instance holds

What you can do with Manticore Search

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Search, 2 operations

  • percolate_searchPercolate searchPOSTPerform reverse search on a percolate table.
  • search_documentsSearch documentsPOSTPerforms a search on a table.

Update, 2 operations

  • partial_update_documentPartial update documentPOSTPartially replaces a document in a table.
  • update_documentsUpdate documentsPOSTUpdate a document in a table.

Autocomplete, 1 operation

  • autocomplete_queryAutocomplete queryPOSTPerforms an autocomplete search on a table.

Delete, 1 operation

  • delete_documentsDelete documentsPOSTDelete a document in a table.

Insert, 1 operation

  • insert_documentInsert documentPOSTCreate a new document in a table.

Replace, 1 operation

  • replace_documentReplace documentPOSTReplace new document in a table.

Sql query, 1 operation

  • run_sqlRun sqlPOSTRuns an SQL statement against Manticore Search and returns its result set.

Use Manticore Search from Claude Code, Cursor or Codex

Connect Manticore Search in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Manticore Search operations become tools the client can call, next to every other integration you connected.

Claude Code
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"
Codex (~/.codex/config.toml)
[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"
Cursor, Claude Desktop and other JSON configs
{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Manticore Search

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect Manticore Search once

    Add your Manticore Search connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. Describe the job in chat

    The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Manticore Search integration FAQ

What can you do with the Manticore Search integration?

LiveContext exposes 9 operations on Manticore Search, covering search, update, autocomplete and delete. Common uses include reading rows with SQL instead of the JSON query DSL, creating or altering a table and inspecting the tables an instance holds.

Popular integrations

Browse the whole catalog