mcp@4.11.0

VERIFIED

Publisher claims: "Crypto social intelligence from X and Telegram, plus the Elfa Auto condition engine" Observed in sandbox: calls api.elfa.ai only, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher elfa-ai · publishing for 106 daysInstalls 1,818Last detonated 19 min ago
$claude mcp add mcp -- npx -y @elfa-ai/mcp
WatchReport an issue

Coverage

Started with a decoy ELFA_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in ELFA_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
ELFA_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
ELFA_API_KEYELFA_MCP_AUTHELFA_OAUTH_INTROSPECTION_TOKENELFA_OAUTH_INTROSPECTION_URLELFA_OAUTH_ISSUERELFA_OAUTH_SCOPESConfiguration, not credentials: ELFA_BASE_URL, ELFA_EXTRA_HEADERS, ELFA_MCP_ALLOWED_HOSTS, ELFA_MCP_ALLOWED_ORIGINS, ELFA_MCP_HOST, ELFA_MCP_MAX_RESPONSE_CHARS, ELFA_MCP_OPENAI_APPS_CHALLENGE, ELFA_MCP_PORT, ELFA_MCP_RESOURCE_URL, ELFA_MCP_TRANSPORT, ELFA_RETRIES, ELFA_TIMEOUT
Where it talks to
elfa.ai (its own)
What the honeypot saw
no credential files read · reached only api.elfa.ai (its own)
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard. It asks for ELFA_API_KEY, ELFA_MCP_AUTH, ELFA_OAUTH_INTROSPECTION_TOKEN, ELFA_OAUTH_INTROSPECTION_URL, ELFA_OAUTH_ISSUER, ELFA_OAUTH_SCOPES and talks to elfa.ai. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --secrets ELFA_API_KEY=elfa.ai,ELFA_MCP_AUTH=elfa.ai,ELFA_OAUTH_INTROSPECTION_TOKEN=elfa.ai,ELFA_OAUTH_INTROSPECTION_URL=elfa.ai,ELFA_OAUTH_ISSUER=elfa.ai,ELFA_OAUTH_SCOPES=elfa.ai -- npx -y @elfa-ai/mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 4.10.0

vet-skills diff mcp 4.10.0 4.11.0

This version reaches for something 4.10.0 did not: 2 new tools (calendar, prediction_markets) · 4 rewritten tool descriptors (auto_draft, auto_draft_write, auto_query, auto_query_write). Compared from the two recorded runs, not from source.

New tools
calendar, prediction_markets
Rewritten tool descriptors
auto_draft, auto_draft_write, auto_query, auto_query_write

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-17 and scored it 93/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: calls api.elfa.ai only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 71 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
31sprocessdependency install exit 0
51sprocessrelaunched with a decoy ELFA_API_KEY (tagged; nothing real)
71snetworkCONNECT tcp://api.elfa.ai:443
71sclaimed18 tools with a decoy ELFA_API_KEY: api_status, entities, events, calendar, prediction_markets, market, calls, top_accounts, auto_build, auto_validate, auto_query, auto_query_write, auto_draft, auto_draft_write, mentions, trending, narratives, market_chat
71stools679d0c242f4a6a96
71stoolsd2810cbc9d96bbe0
71stools1af4ab6b506d4d8f
71stools0dbcd9e06403add5
71stools985431d16dee8eca
71stools90c180071b86079c
71stools12e2512bdbd457ea
71stools19815bcbfc3deb85
71stoolsa273fc900df4d335
71stoolsd5cb077b51dc39ff
71stoolsc12cdae974e8b76b
71stoolsf05e94daf24e1a7c
71stools751df2cf63caf62b
71stools82cac0c707661976
71stools7485a71fbbe9fa94
71stools6fbf4bd409f8fefc
71stoolsce46a140a4766494
71stoolsd3d11d4473cae7e1
71sprocessscript backend runs setup only
71sprocessno install scripts to re-run

Static findings

No findings across 3,332 lines in 8 files.

Cost to the agent

Instructions loaded
≈60 tok
1 file · 8 in bundle
Tool list per prompt
≈7,742 tok
18 tools · 430 per tool
Handshake
2935 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 430

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.