Compare agents

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.

Comparison dimension	Repo Health Check An MCP server that gives any public GitHub repository a maintainer-health score from 0 to 100, and shows its working.	Mobile QA Tester Finds what your change left untested, and the device cases nobody runs.	Mobile Intake Interviewer Runs the intake interview one question at a time and freezes the brief.
Made of	Code	Instructions · Skills	Instructions · Skills
Connection	Hosted sandbox or your machine	Hosted (connect over the gateway)	Hosted (connect over the gateway)
Category	Software Development	Software Development	Software Development
Price	Free	Free	Free
What it does	No tools declared	6 tools 6 read-only assess_coverage design_test_cases check_test_quality plan_device_matrix report_bug draft_test_report	8 tools 8 read-only discover_intent list_capabilities open_brief ask_next_question record_answer assess_readiness +2 more
Keys it asks for	No keys required	No keys required	No keys required
Guardrails	Platform defaults only	Platform defaults only	Platform defaults only
Rating	Not rated yet	Not rated yet	Not rated yet
Security	Runs hosted in a sandbox or on your own machine · scanned and human-reviewed Capability: Offered to run on YOUR machine too: if you download and run it locally, FindAgent does not run it — it executes with your own access, not in the sandbox. Review the source before running it locally. Guaranteed: For a local run, FindAgent never holds the keys — any credentials stay on your own machine. Guaranteed: If you connect it hosted, FindAgent runs the creator's code only in an isolated, single-use sandbox — never on your machine. Guaranteed: That hosted sandbox starts with no network access — it can reach only the hosts this agent declares, nothing else. Capability: Its code can reach api.github.com. Guaranteed: Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Guaranteed: Passed an automated security scan and a human review before it could be published.	Ships no code · scanned and human-reviewed Guaranteed: Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours. Guaranteed: Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Capability: Its tools only read data — none of them create, change, or delete anything. Guaranteed: Passed an automated security scan and a human review before it could be published.	Ships no code · scanned and human-reviewed Guaranteed: Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours. Guaranteed: Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Capability: Its tools only read data — none of them create, change, or delete anything. Guaranteed: Passed an automated security scan and a human review before it could be published.

Compare agents

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.

Comparison dimension	Repo Health Check An MCP server that gives any public GitHub repository a maintainer-health score from 0 to 100, and shows its working.	Mobile QA Tester Finds what your change left untested, and the device cases nobody runs.	Mobile Intake Interviewer Runs the intake interview one question at a time and freezes the brief.
Made of	Code	Instructions · Skills	Instructions · Skills
Connection	Hosted sandbox or your machine	Hosted (connect over the gateway)	Hosted (connect over the gateway)
Category	Software Development	Software Development	Software Development
Price	Free	Free	Free
What it does	No tools declared	6 tools 6 read-only assess_coverage design_test_cases check_test_quality plan_device_matrix report_bug draft_test_report	8 tools 8 read-only discover_intent list_capabilities open_brief ask_next_question record_answer assess_readiness +2 more
Keys it asks for	No keys required	No keys required	No keys required
Guardrails	Platform defaults only	Platform defaults only	Platform defaults only
Rating	Not rated yet	Not rated yet	Not rated yet
Security	Runs hosted in a sandbox or on your own machine · scanned and human-reviewed Capability: Offered to run on YOUR machine too: if you download and run it locally, FindAgent does not run it — it executes with your own access, not in the sandbox. Review the source before running it locally. Guaranteed: For a local run, FindAgent never holds the keys — any credentials stay on your own machine. Guaranteed: If you connect it hosted, FindAgent runs the creator's code only in an isolated, single-use sandbox — never on your machine. Guaranteed: That hosted sandbox starts with no network access — it can reach only the hosts this agent declares, nothing else. Capability: Its code can reach api.github.com. Guaranteed: Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Guaranteed: Passed an automated security scan and a human review before it could be published.	Ships no code · scanned and human-reviewed Guaranteed: Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours. Guaranteed: Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Capability: Its tools only read data — none of them create, change, or delete anything. Guaranteed: Passed an automated security scan and a human review before it could be published.	Ships no code · scanned and human-reviewed Guaranteed: Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours. Guaranteed: Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Capability: Its tools only read data — none of them create, change, or delete anything. Guaranteed: Passed an automated security scan and a human review before it could be published.