Funkel AI

Q: Is Funkel AI MCP server safe?

QAmcp's test on 22 Oct 2026: No hidden instructions were found in its tool descriptions. Its error messages showed no secrets or internal details. 29 of its 51 tools are labeled read-only; the others may change or send things. Overall it scored 84/100 on 22 Oct 2026. A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

by funkel.ai · https://api.funkel.ai/mcp

Run LinkedIn and email outreach: find leads, manage campaigns, and reply to prospects.

51 tools✓ no account neededPricing: on their site

See pricing →Visit website

84 /100

PASS · WITH NOTES

Partial: 8 of 10 checks · 22 Oct 2026

Is Funkel AI MCP server safe?

No hidden instructions were found in its tool descriptions.
Its error messages showed no secrets or internal details.
29 of its 51 tools are labeled read-only; the others may change or send things.
Overall it scored 84/100 on 22 Oct 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What it can do

51 tools, in the server's own words.

list_appsread-only

List the products/apps owned by the request scope's user.

get_product_contextread-only

Read the selected product's name, site, description, ICP summary, language, Product Brain availability, and dashboard link.

list_listsread-only

List unarchived lead lists in the selected product.

get_listread-only

Read one unarchived list in the selected product and its exact member count.

list_list_contactsread-only

List contacts in one unarchived list in the selected product.

get_scheduleread-only

List pending, approved, or failed scheduled actions in the selected product, optionally for one campaign.

get_scheduled_actionread-only

Read one action in the selected product: campaign, lead, type, state, scheduled and executed timestamps.

list_remindersread-only

List open or done lead reminders in the selected product with exact total and bounded pages.

list_insightsread-only

List account-scoped and selected-product-scoped open insights.

get_insightread-only

Read one insight and its evidence for the selected product, or an explicitly account-scoped insight.

list_operator_tasksread-only

List durable Operator tasks in the selected product.

get_operator_taskread-only

Read one durable Operator task in the selected product with its step states, action states, safe summaries, version, and progress.

get_accessread-only

Read current account access for Operator and campaign actions in the selected product.

create_note

Create a scoped note or reminder after an explicit confirmation of the exact lead, body, and due date.

create_reminder

Create a scoped note or reminder after an explicit confirmation of the exact lead, body, and due date.

save_preference

Save one selected-product Operator preference after explicit approval.

rename_list

Rename one unarchived list in the selected product after explicit approval.

control_operator_task

Pause, resume, cancel, or retry a durable Operator task after exact approval.

list_agentsread-only

List the specialist agents in the product/app the request is scoped to.

get_agent_sourcesread-only

Read X and Hacker News listening settings for one owned agent, including sources not configured yet.

set_agent_source_listening

Pause or resume only an existing X or Hacker News source on an agent.

configure_agent_source

Configure X or Hacker News searches for one owned agent and set source listening.

list_campaignsread-only

List the campaigns in the app the request is scoped to (excludes archived).

get_campaignread-only

Read one campaign in the selected product.

and 27 more

Test results

Safe mode: only tools labeled read-only were run. How the test works

!
Ready for the newest MCP version
1 warning
- !Uses an older MCP version (2025-06-18). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described
3 warnings
- !set_agent_source_listening: Inputs with no description: enabled
- !create_note and create_reminder have nearly the same description (100% of their words are shared; the descriptions are identical), so an AI may not know which to pick
- !pause_campaign and pause_agent have nearly the same description (76% of their words are shared; the only difference: "campaign", "engine", "scheduling" vs "agent", "discovering", "new"), so an AI may not know which to pick
note
✓
ConnectsConnected in 1.1 s
pass
✓
Lists its toolsFound 51 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
pass
✓
No hidden instructionsNo hidden instructions found in tool descriptions
pass
✓
Fast enough
All good
- ✓Connecting took 1.1 s
- ✓Listing tools took 174 ms
pass
✓
No secrets leakedChecked 59 error messages: no secrets or internal details
pass
–
Tools work with good inputs
Not tested
- –list_apps: Needs you to sign in, so it was not tested (not counted against the server)
- –get_product_context: Needs you to sign in, so it was not tested (not counted against the server)
- –list_lists: Needs you to sign in, so it was not tested (not counted against the server)
- –get_list: Needs you to sign in, so it was not tested (not counted against the server)
- –list_list_contacts: Needs you to sign in, so it was not tested (not counted against the server)
- –get_schedule: Needs you to sign in, so it was not tested (not counted against the server)
- –get_scheduled_action: Needs you to sign in, so it was not tested (not counted against the server)
- –list_reminders: Needs you to sign in, so it was not tested (not counted against the server)
- and 32 more
not tested
–
Bad inputs give a clean error
Not tested
- –list_lists: Needs you to sign in, so bad inputs were not tested
- –get_list: Needs you to sign in, so bad inputs were not tested
- –list_list_contacts: Needs you to sign in, so bad inputs were not tested
- –get_schedule: Needs you to sign in, so bad inputs were not tested
- –get_scheduled_action: Needs you to sign in, so bad inputs were not tested
- –list_reminders: Needs you to sign in, so bad inputs were not tested
- –list_insights: Needs you to sign in, so bad inputs were not tested
- –get_insight: Needs you to sign in, so bad inputs were not tested
- and 11 more
not tested
–
Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)
not tested

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://api.funkel.ai/mcp

Score over time

17 Oct 202684
18 Oct 202684
22 Oct 202684

Reviews

Coming soon: reviews from people who use Funkel AI, signed in with GitHub, one per person. Reviews never change the score.

Is this your server?

Soon you can claim this page: re-test it from here, reply to results, and show a "Tested by QAmcp" badge.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works