Elfa MCP — Watchlist | MCP100 Index

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Elfa crypto-social intelligence and condition-triggered actions: Do Auto execution permissions remain distinguishable from read-only market and social observations?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Crypto social intelligence plus a condition engine for monitoring market conditions.

What we know

Official Elfa MCP exposing social mentions/trending/narratives/market analysis and Auto condition-engine tools. Auto activation is a deliberate write step.

Maintenance / activity evidence

@elfa-ai/mcp 4.5.0 published 2026-10-05T13:49:46.200Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Read market/social data plus activation/parking of Auto plans. Writes: Arm/activate Auto monitoring plans; Park/modify Auto plans where exposed.
Elfa API key.
Sensitive access: Market strategy, Social intelligence, API key

Auto writes can create ongoing monitoring behavior; show user cost/action before activation.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do Auto execution permissions remain distinguishable from read-only market and social observations?

The bounded review of the publisher's documented Elfa crypto-social intelligence and condition-triggered actions and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Auto writes can create ongoing monitoring behavior; show user cost/action before activation.
Read market/social data plus activation/parking of Auto plans.
Elfa API key.
Queries and third-party social/news data go through Elfa.
Reviewed write actions: Arm/activate Auto monitoring plans; Park/modify Auto plans where exposed
Sensitive access: Market strategy, Social intelligence, API key
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
Requires API key and consumes credits.
LLM-backed interpretation calls can be slow and billed even if client times out.
Third-party social/news text is untrusted.
Armed Auto queries keep evaluating without prompting again.

Original activity observations

@elfa-ai/mcp 4.5.0 published 2026-10-05T13:49:46.200Z

Technical identity

npm/@elfa-ai/mcp

Exact implementation source: https://www.npmjs.com/package/@elfa-ai/mcp ↗
Reviewed resource type: MCP Server
Repository identity: elfa-ai/mcp
Package identity: npm:@elfa-ai/mcp

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry metadata ↗
@elfa-ai/mcp
Recorded package identity, distribution or download evidence.
Evidence source ↗
docs.elfa.ai/mcp/
Source material retained for this review.
Includes references whose attribution is not established.
GitHub repository ↗
elfa-ai/mcp
Repository reference; implementation attribution is not established for every document.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
ELFA_API_KEY required in stdio mode; optional self-hosted HTTP mode.
publisher install or stdio launch · Claude Code only · Publisher instructions
claude mcp add elfa --env ELFA_API_KEY=your-key -- npx -y @elfa-ai/mcp
Configure / authenticate
MCP100 setup guide
Publisher `claude mcp add elfa --env ELFA_API_KEY=<key> -- npx -y @elfa-ai/mcp`.
Check connection
Suggested check
Use free read-only `api_status` to confirm key and remaining credits.
Remove / uninstall / revoke
MCP100 setup guide
For a Claude Code registration named `elfa-ai-mcp`, run `claude mcp remove elfa-ai-mcp`; otherwise remove the exact entry in the chosen MCP client settings and restart/reconnect. This client-host removal command is MCP100-composed from Claude Code lifecycle documentation, not a vendor-authored uninstall. With `npx`, a separate global package uninstall normally is unnecessary. Do not delete provider data or credentials by default.
Client unregister, package uninstall, data deletion, and OAuth/API token/wallet permissions are distinct.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove elfa-ai-mcp

Official Documentation & Sources

What it does

Official Elfa MCP exposing social mentions/trending/narratives/market analysis and Auto condition-engine tools. Auto activation is a deliberate write step.

Capability: Finance & Payments
Resource type: MCP Server
Industry: Financial Services & Investing
Best fit: Crypto social intelligence plus a condition engine for monitoring market conditions.

Representative uses

Read trending tokens and mentions
Analyze narratives/market chat
Build/validate market conditions
Arm Auto queries after reviewing cost/action

Limitations

Requires API key and consumes credits.
LLM-backed interpretation calls can be slow and billed even if client times out.
Third-party social/news text is untrusted.
Armed Auto queries keep evaluating without prompting again.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Elfa API key.
Permissions: Read market/social data plus activation/parking of Auto plans.
Data handling: Queries and third-party social/news data go through Elfa.
Cost: credit_based
Risk and cautions: Auto writes can create ongoing monitoring behavior; show user cost/action before activation.

Access scope and cautions

Write actions: Arm/activate Auto monitoring plans Park/modify Auto plans where exposed
Sensitive access: Market strategy Social intelligence API key
Risk level: high

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Read trending tokens and mentions; Analyze narratives/market chat; Build/validate market conditions; Arm Auto queries after reviewing cost/action.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @elfa-ai/mcp. Recorded transport: stdio. Recorded environment-variable notes: ELFA_API_KEY; ELFA_TIMEOUT (optional); ELFA_RETRIES (optional); ELFA_MCP_MAX_RESPONSE_CHARS (optional); ELFA_EXTRA_HEADERS (optional). No configuration values are supplied here. Prerequisites: MCP client. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Elfa API key.

Can it modify data or perform write operations?

Documented write actions include: Arm/activate Auto monitoring plans; Park/modify Auto plans where exposed. Recorded permission boundary: Read market/social data plus activation/parking of Auto plans.

What data-handling boundary should I consider?

Queries and third-party social/news data go through Elfa. Recorded sensitive-access context: Market strategy; Social intelligence; API key.

What limitations and risks should I check before use?

Auto writes can create ongoing monitoring behavior; show user cost/action before activation. Requires API key and consumes credits. LLM-backed interpretation calls can be slow and billed even if client times out. Third-party social/news text is untrusted. Armed Auto queries keep evaluating without prompting again. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.

What cost model is recorded?

The reviewed cost model is credit based. This classification does not establish current prices, quotas or the cost of every downstream operation. Check the applicable service terms before authorizing paid actions.