Elfa MCP

Model Context Protocol server for the Elfa API — crypto social intelligence from X and Telegram, plus Auto, a condition engine that watches the market and fires an action when your conditions are met.

Works with any MCP client: Claude Code, Claude Desktop, Cursor, VS Code, Codex, and anything else that speaks MCP.

Install

Get an API key at dev.elfa.ai. No install step — npx fetches the server on demand.

One click

Claude Desktop

Download elfa-mcp-<version>.mcpb from the latest release and open it. Claude Desktop installs it, prompts for your API key, and keeps it updated. Nothing else to configure.

Claude Code

claude mcp add elfa --env ELFA_API_KEY=your-key -- npx -y @elfa-ai/mcp

Cursor, VS Code, Claude Desktop, and other clients

{
  "mcpServers": {
    "elfa": {
      "command": "npx",
      "args": ["-y", "@elfa-ai/mcp"],
      "env": {
        "ELFA_API_KEY": "your-key"
      }
    }
  }
}

VS Code uses "servers" instead of "mcpServers". Everything else is the same.

Ask "what's trending in crypto right now?" to confirm it works.

Configuration

The timeout is high and retries are off on purpose. The interpretation endpoints are LLM-backed and can take over a minute, and they cost credits per attempt, so a silent retry would bill you again for a call you never saw. Raise ELFA_RETRIES only if you are calling the cheap measurement endpoints.

Some MCP clients apply their own timeout, often around 60 seconds. narratives and market_chat can exceed that; the request still completes and is still charged, even if the client gives up first.

Tools

11 tools, mapped to every documented /v2 operation.

Not exposed as tools:

• chat-stream-v2 — A tool call returns one result, so streaming adds nothing. market_chat covers the same analysis.
• auto-stream-queries-v2 — Long lived streams have no tool equivalent. Poll with auto_query.
• auto-stream-query-v2 — Long lived streams have no tool equivalent. Poll with auto_query.

Some tools depend on the plan: today market_chat, which needs a higher-tier plan than the free one. At startup (stdio) or per request (HTTP, cached for a minute per key), the server reads the key's scopes from /v2/key-status. A tool the plan doesn't include stays listed, but its description says it needs a higher-tier plan, and calling it returns the upgrade link without calling the API or spending credits. If the scopes can't be read within 3 seconds, every tool is listed as usual and the API decides.

Streaming endpoints stay available through the SDKs for applications that can consume SSE.

Where this differs from the raw API

The tools deliberately do not inherit every API default, because an agent pays for verbosity in context.

Every value is still settable per call, and pageSize accepts up to 100.

Auto

Auto queries run unattended. Once armed, a query keeps evaluating and fires its action without asking again.

The flow is three steps:

1. auto_build — describe what to watch in plain language, get EQL back
2. auto_validate — check the syntax and get the credit cost
3. auto_query_write — activate it

Actions can notify you, call a webhook, message a Telegram bot, or run an LLM analysis.

There is no push channel over MCP. Poll auto_query with method=get, and wait for the returned pollAfterSeconds between calls.

Remote server

The same server runs over Streamable HTTP for hosted deployments:

ELFA_MCP_TRANSPORT=http ELFA_MCP_PORT=3000 npx -y @elfa-ai/mcp

It is stateless — no sessions, one server instance per request, safe behind a load balancer. Credentials come from the x-elfa-api-key request header, falling back to the environment, or from an OAuth sign-in (see below).

DNS rebinding protection is on by default. The server accepts only the loopback names it binds — localhost:PORT and 127.0.0.1:PORT — which covers the local run above and nothing else. Any deployment that answers on a different Host must list the values it serves:

ELFA_MCP_ALLOWED_HOSTS=mcp.example.com

That includes a public domain, a reverse proxy, and a container that maps the port to a different one than the server binds. A Host the list does not cover is rejected with 403.

Set ELFA_MCP_ALLOWED_ORIGINS as well when browsers call the server directly. It complements the host allowlist rather than replacing it: a rebound request is same origin, so it carries no Origin header for that list to check, and the Host header is the only one still naming the attacker's domain.

OAuth sign-in

A hosted server can let clients sign in through a browser instead of sending an API key. Set ELFA_MCP_AUTH=oauth and the server becomes an OAuth resource server under the MCP authorization spec:

1. A request with no credential gets 401 and a WWW-Authenticate challenge.
2. The challenge points the client to the protected-resource metadata at /.well-known/oauth-protected-resource/mcp.
3. That metadata names the authorization server, where the user signs in.
4. The client then sends Authorization: Bearer <token>.
5. The server checks the token against the authorization server's introspection endpoint. The endpoint answers with the Elfa API key the request runs as, so the token never reaches the Elfa API.

ELFA_MCP_TRANSPORT=http \
ELFA_MCP_AUTH=oauth \
ELFA_MCP_RESOURCE_URL=https://mcp.example.com/mcp \
ELFA_OAUTH_ISSUER=https://auth.example.com \
ELFA_OAUTH_INTROSPECTION_URL=https://auth.example.com/introspect \
ELFA_OAUTH_INTROSPECTION_TOKEN=... \
ELFA_MCP_ALLOWED_HOSTS=mcp.example.com \
npx -y @elfa-ai/mcp