mcp@10.21.0

VERIFIED

Publisher claims: "Model Context Protocol server for FerrFleet: agents, runs, skills" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher ferrfleet · publishing for 47 daysInstalls 2,926Last detonated 1 h ago
$claude mcp add mcp -- npx -y @ferrfleet/mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
ferrfleet.com (its own)
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Reasonable to connect. No credential asked for, no third-party host named, Server started and answered tools/list.

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

What changed since 10.17.2

vet-skills diff mcp 10.17.2 10.21.0

This version reaches for something 10.17.2 did not: 9 rewritten tool descriptors (create_agent, create_event_rule, create_workflow, get_run, …). Compared from the two recorded runs, not from source.

Rewritten tool descriptors
create_agent, create_event_rule, create_workflow, get_run, list_runs, run_workflow, update_agent, update_event_rule, update_workflow

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 2026-11-16 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: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 25 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
5.0sprocessdependency install exit 0
25sclaimed36 tools: list_agents, get_agent, trigger_agent_run, create_agent, update_agent, list_connectors, create_connector, set_agent_connectors, update_connector, list_event_rules, create_event_rule, update_event_rule, delete_event_rule, reorder_event_rules, list_event_decisions, list_github_installations, create_github_connector, list_marketplace_agents, import_marketplace_agent, list_ferrfleet_orgs, list_repo_bindings, bind_repo, list_runner_pools, list_runs, get_run
25stools5bf004a88f2ba2eb
25stoolse551c5c976f4e51e
25stools26b3aeee044a80ef
25stoolsbb54ee6294b87e7e
25stools10329084296a12e9
25stools6417695c0597ac3c
25stoolsf8b2c9037c19bd49
25stools3d5ebc78d18b743d
25stools022bba0bf47ea9cc
25stoolsd30df5eb77cdf146
25stoolsfeb2cd6525eb7447
25stools0ab681f88324ffb4
25stools482b39ff68757869
25stools707cf090884d5551
25stools7d07db492d41c2e1
25stoolsb8b4a138d4f10e42
25stools65ac5b5436ee20f0
25stools735c5affa1e91ab2
25stools07034b6bcadb0f46
25stools8bafd96b61f19fa5
25stools8e3fe8a40e2bfc8e
25stools2f54c04345c5a722
25stoolse54f0104bf173fdf
25stools6f5b6413921778b5
25stools464e13eb54cb95f1
25stools3aa3713440901feb
25stoolsdeeb012ebeaaa341
25stools814057bc71e578e4
25stoolsb227ce193aaa435b
25stools9e0ccdf51b59d3d5
25stools95f4341e48bfd66c
25stools62cda28d635a0208
25stools89864bb7b4832be6
25stools0b93da64420f27ef
25stools53d904e9d3468c72
25stools91f461e61ec6b57f
25sprocessscript backend runs setup only
25sprocessno install scripts to re-run

Static findings

No findings across 2,498 lines in 40 files.

Cost to the agent

Instructions loaded
≈51 tok
1 file · 40 in bundle
Tool list per prompt
≈11,883 tok
36 tools · 330 per tool
Handshake
1048 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 196

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.