MCP server

by elfa.ai·ai.elfa/mcp·v4.1.0

No reviews yet

Crypto social intelligence from X and Telegram, plus the Elfa Auto condition engine

B83/100grade B

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

B83/100

full report

Adoption

Growing

7 stars37 downloads/wk

Reviews

Write one

Nobody has reviewed MCP yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

MCP tools (11, 1 write)

write = sends, deletes, buys or posts

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

account_stats
Smart follower and engagement stats for an X account. 1 credit per call. Use it to judge whether an account's reach is real before weighting what it posts. Returns raw metrics, not a reputation score, so the signal is in the ratios. Legacy: it still works today and keeps working until 28 October 2026, when it will be removed, and it is not being extended before then. Build new work on mentions wit
api_status
Check the Elfa API key tier, credit usage and remaining requests, and confirm the API is reachable. Free. Call this first when a request fails with an auth or credit error.
auto_build
Turn a plain-language monitoring request into an EQL query. Costs 1 credit plus LLM usage. This only drafts the query, nothing starts running until you activate it with auto_query_write. Say what to watch, the threshold, and what should happen when it fires.
auto_draft
Park an Auto query without activating it. Drafts never evaluate and never fire. Free, except method=convert which activates the draft and costs the same as creating a query. Use drafts when the user is still deciding.
auto_query
Read side of Auto. Free. method=list browses queries, method=get polls one query and returns its latest evaluation, method=executions and method=execution show what fired, method=sessions and method=session return the LLM analysis attached to a query. There is no push channel here, poll with method=get and respect pollAfterSeconds.
auto_query_writewrite action
Activate, cancel or delete an Auto query. Creating costs 5 credits plus LLM usage, cancel and delete are free. An activated query runs unattended and fires its action without asking again, so validate it with auto_validate and confirm the cost and the action with the user before calling this.
auto_validate
Check EQL syntax and get a cost estimate before anything is activated. Free. Always run this before auto_query_write, and show the estimated cost to the user. Pass either an inline query or a draftId. method=symbol instead checks that a symbol has market data on a venue, before you build price or ta conditions around it.
market_chat
Ask Elfa for written market analysis grounded in its social data. Costs credits and varies by speed, so fast is the cheaper option. Pass sessionId from a previous reply to continue the same conversation.
mentions
Social mentions from X and Telegram. 1 credit per call. Returns engagement metrics and a link per post, not the post text. mode=top ranks one ticker's mentions by engagement. mode=search filters by keywords or by account. mode=news returns the token news feed, which is X posts from accounts tagged as news sources rather than articles from news outlets.
narratives
Written narrative analysis with source links, for when counts are not enough. 5 credits per call, so prefer trending or mentions when metrics will do. scope=market extracts the narratives moving the market. scope=keywords summarises events for keywords you supply, and can take over a minute to return.
trending
What is gaining social attention right now. 1 credit per call. scope=tokens returns tickers ranked by mention volume with the change against the previous window. scope=contracts_twitter and scope=contracts_telegram return trending contract addresses.

Public scan report

scanner v0.1.9 · 2026-09-22 · same rubric, same numbers if you re-run it

no findings

Code scan4 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
Maintenancelast push 0 days ago15/15
Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace8/10

Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

What the publisher says

From the MCP repository's README, as published. We do not edit it. Read it on GitHub

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-.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.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y @elfa-ai/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y @elfa-ai/mcp

Add to Cursor

MCP: common questions

Is MCP server safe?: Mostly: it is graded B (83/100). Read the MCP safety report
How do I install MCP?: It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does MCP need an API key?: Yes. The registry entry asks for ELFA_API_KEY.
Is MCP maintained?: The last commit was in the last day (2026-09-22). The latest release is v4.1.0.
What can I use instead of MCP?: Servers from other publishers that do the same job: Hive Intelligence MCP server, CoinRithm Agent Trading MCP server and MCP server. Compare all MCP alternatives.

Alternatives to MCP

Same job from other publishers: the closest match first, then the best rated.

All MCP alternatives →

Hive Intelligence MCP
Evidence-backed crypto due diligence with sources, freshness, and a runtime receipt on every call.
not reviewed
Established
B
CoinRithm Agent Trading
Keyless prediction-market data across 12 venues plus paper-trading of crypto spot, futures, and PM.
not reviewed
Growing
B
MCP
Crypto market intelligence: prices, funding rates, narratives, regime, and delta-neutral research.
not reviewed
Growing
A
Daepak Market Intelligence
Market analyst tools + AI agent: crypto, US equities, options, Korea, fundamentals, macro, backtests
not reviewed
Growing
C
RiskState — Crypto Risk Engine
Live BTC/ETH risk state: risk policy, market structure and trading playbooks. Keyless free tier.
not reviewed
Growing
A

MCP vs Hive Intelligence MCP MCP vs CoinRithm Agent Trading MCP vs MCP