A side-by-side look at what each agent does, the keys it asks for, and how it keeps you safe. Every fact below is derived from the agent’s own listing — no score, no ranking.
FullYou can compare up to 3 agents. Remove one to add another.
Finds deals that stopped moving, and separates waiting-on-them from waiting-on-us.
Type
Doer
Doer
Doer
Connection
Hosted (connect over the gateway)
Hosted (connect over the gateway)
Hosted (connect over the gateway)
Category
Customer Service
Customer Service
Customer Service
Price
Free
Free
Free
What it does
6 tools
3 read-only · 3 write
list_sla_policies
search_open_tickets
get_ticket_metrics
post_sla_alert
trigger_pagerduty_incident
mark_ticket_alerted
8 tools
6 read-only · 2 write
get_ticket
list_ticket_comments
search_help_center
get_article
search_solved_tickets
compose_deflection_reply
+2 more
5 tools
3 read-only · 2 write
search_stalled_deals
get_deal
get_deal_activity
get_note
post_stalled_digest
Keys it asks for
Zendesk API credentialSent only to zendesk.com
Slack bot tokenSent only to slack.com
PagerDuty REST API keySent only to api.pagerduty.com
Zendesk API credentialSent only to zendesk.com
HubSpot private app tokenSent only to api.hubapi.com
Slack bot tokenSent only to slack.com
Guardrails
Input rail
Action rail
Output rail
Input rail
Action rail
Output rail
Input rail
Action rail
Output rail
Rating
Not rated yet
Not rated yet
Not rated yet
Security
Ships no code · your key only reaches zendesk.com, slack.com, +1 more · scanned and human-reviewed
Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours.
Any key you connect is bound to its destination — it is only ever sent to zendesk.com, slack.com, api.pagerduty.com, and is dropped if a request tries to redirect it elsewhere.
Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no listing can turn off.
Some tools can create, change, or delete data in your connected accounts — your AI client asks you to confirm before a change runs.
Passed an automated security scan and a human review before it could be published.
Ships no code · your key only reaches zendesk.com · scanned and human-reviewed
Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours.
Any key you connect is bound to its destination — it is only ever sent to zendesk.com, and is dropped if a request tries to redirect it elsewhere.
Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no listing can turn off.
Some tools can create, change, or delete data in your connected accounts — your AI client asks you to confirm before a change runs.
Passed an automated security scan and a human review before it could be published.
Ships no code · your key only reaches api.hubapi.com, slack.com · scanned and human-reviewed
Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours.
Any key you connect is bound to its destination — it is only ever sent to api.hubapi.com, slack.com, and is dropped if a request tries to redirect it elsewhere.
Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no listing can turn off.
Some tools can create, change, or delete data in your connected accounts — your AI client asks you to confirm before a change runs.
Passed an automated security scan and a human review before it could be published.