WarpSearch MCP

WarpSearch MCP enables AI agents to perform serverless hybrid search, including full-text, vector, and faceted queries. Agents can register users, create collections, index documents, and execute searches using SQL, Elasticsearch DSL, or Solr syntax via a streamable HTTP transport.

Visit WarpSearch

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.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-01Published by WarpSearch

MCP endpoint (Streamable HTTP)

https://api.warpsearch.io/mcp

Vendor documentation

What you can do with it

Register a new user and obtain an API key via email approval
Create collections and define schemas for indexing documents
Index JSON documents into collections for searchability
Execute hybrid searches using SQL, ES DSL, or Solr queries

Source and maintenance

Community listingRegistry 07c29b2c5d6b306682ac528fc1111fc301ce64f4

mcp-registry: io.github.warpsearchio/warpsearch@07c29b2c5d6b306682ac528fc1111fc301ce64f4 Project website

Protocol and capabilities

Server: warpsearch-gateway 07c29b2c5d6b306682ac528fc1111fc301ce64f4
MCP protocol: 2025-06-18
Tools: 2 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  },
  "logging": {}
}

Server-provided instructions

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

WarpSearch is a serverless hybrid search service: full-text (BM25), vector and faceted search over JSON documents, plus analytics (facets, metrics, date histograms), graph neighborhood retrieval and shortest paths. It understands SQL (MySQL and PostgreSQL dialects, with tsquery full text and pgvector distances), Elasticsearch/OpenSearch Query DSL, Apache Solr, Lucene, Grafana, LogQL and its native WarpSearch language, so query it in the language you know best. Data lives in collections: index JSON documents into one, then search it. Use it as a search backend for an app, for log and event analytics, or as memory you can search. You are connected without credentials, so only account registration is available here. - If your user already has a WarpSearch API key (ws_live_...), reconnect to this server with the header "Authorization: Bearer <key>". - Otherwise, call register with your user's email address. Use only an address your user gave you for this, with their consent; never guess one. WarpSearch emails them; in their browser they create the account if they have none, check the code you show them, and approve your access. Then call claim_registration for an API key and reconnect with it.

Tools

2 advertised

claim_registration — Claim registration

Advertised by the server during the last successful anonymous check.

Check on a registration, and receive the API key once your user has approved it. Returns status: pending (not approved yet; ask your user to finish, then call again), approved (with api_key, shown only this once, and how to reconnect with it), denied, expired, or claimed (the key was already handed out).

claim_registration input schema

{
  "type": "object",
  "required": [
    "claim_token"
  ],
  "properties": {
    "claim_token": {
      "type": "string",
      "description": "the claim_token register returned"
    }
  },
  "additionalProperties": false
}

claim_registration annotations

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

register — Register for WarpSearch

Advertised by the server during the last successful anonymous check.

Open-world

Ask WarpSearch for an account and an API key for your user. Use only an email address your user gave you for this, with their consent. The address must be a work address at your user's organization's own domain. Personal and free mailbox providers (gmail.com, outlook.com, hotmail.com, yahoo.com, icloud.com, proton.me, disposable addresses and the like) are refused with code personal_email during the public preview; ask your user for their work address instead of retrying. WarpSearch emails that address. Your user follows the link, creates the account if they have none, checks that the code matches the user_code you show them, and approves, choosing the organization and the role you get. Nothing is created until they approve, and the answer is the same whether or not the address already has an account. Returns user_code (show it to your user), claim_token (keep it secret; pass it to claim_registration), expires_at and next_steps. Each address gets at most 3 sign-up emails an hour.

{
  "type": "object",
  "required": [
    "email"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "your user's name, if you know it (used in the email)"
    },
    "role": {
      "type": "string",
      "description": "the role you ask for: admin (default; can also delete collections), editor (can also create collections and change mappings), writer (index into existing collections) or viewer (search only). Your user may lower it"
    },
    "agent": {
      "type": "string",
      "description": "who you are, e.g. 'Claude Code on Ada's laptop'; shown to your user when they approve"
    },
    "email": {
      "type": "string",
      "description": "your user's work email address, exactly as they gave it to you for this; free and personal mailbox providers (gmail.com, outlook.com, ...) are refused"
    }
  },
  "additionalProperties": false
}

{
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "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: 1170 ms
95th percentile latency: 1170 ms

Maintenance history

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

Nov 1, 2026, 7:03 AM UTC · probe · passed · 1170 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 warpsearch-mcp https://api.warpsearch.io/mcp

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 warpsearch-mcp --url https://api.warpsearch.io/mcp

Cursor

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

Cursor configuration

{
  "mcpServers": {
    "warpsearch-mcp": {
      "url": "https://api.warpsearch.io/mcp"
    }
  }
}

Cline

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

Cline configuration

{
  "mcpServers": {
    "warpsearch-mcp": {
      "type": "streamableHttp",
      "url": "https://api.warpsearch.io/mcp",
      "disabled": false
    }
  }
}

VS Code

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

VS Code configuration

{
  "servers": {
    "warpsearch-mcp": {
      "type": "http",
      "url": "https://api.warpsearch.io/mcp"
    }
  }
}

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 warpsearch-mcp https://api.warpsearch.io/mcp

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": {
    "warpsearch-mcp": {
      "url": "https://api.warpsearch.io/mcp"
    }
  }
}

Windsurf

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

Windsurf configuration

{
  "mcpServers": {
    "warpsearch-mcp": {
      "serverUrl": "https://api.warpsearch.io/mcp"
    }
  }
}

Let your agent find its tools

Find servers like WarpSearch 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 3,759