An agent researched all 100. Auth scheme, whether an outside developer can actually get a credential, API surface, existing MCP, and a buildability call with evidence behind each one. Then I graded it against 100 labels I wrote by hand, and against Composio's own catalog. Findings, agent, and the proof it's trustworthy are all on this page.
I joined the research set against Composio's live catalog through the v3 API. That turns a table into a build queue. What an engineer starts tomorrow, and what's a partnerships call instead.
Apps missing from the catalog, ranked. Score = credential access (40) + API surface (25) + auth effort (15) + evidence confidence (10) + agent-readiness (10). Hover a score for the breakdown. The weights are my judgement, written down so you can argue with them.
Sorted by the share of apps where a developer can issue their own credential. Every cell prints its number, so colour never carries meaning alone.
The 100 skew enterprise by design, and it shows.
Open at the top, closed at the bottom.
Every judgement carries the URL it came from. Rows I graded by hand are tagged gold. Rows a real browser visited are tagged browser.
About 900 lines of Python. Pass 1 is the control, not a stage. It's what this assignment looks like if you just ask a model, and it's here so the final number has something to beat.
Measured on the final grounded run over all 100 apps. The control pass, the browser pass and the API probe aren't counted, and neither are the runs I threw away.
Three measurements, kept separate on purpose. 20 apps I labelled by hand from primary sources before writing any grading code. A cross-check against Composio's shipped auth config on every app it already covers. And a real browser on the pricing pages, for the one field docs never state.
Same 20 apps, same 100 labels, every stage.
Bucketed by what the agent claimed for that field before it knew the answer.
Nothing filtered. Abstained means it said unknown instead of guessing, which is the better way to be wrong.
Composio turns apps into things agents can call. Handing in research about that as a PDF would be odd. The dataset behind this page runs as an MCP server, so you can ask it questions instead of reading it.
Five tools: search_apps, get_app,
build_queue, patterns, verification. Try:
"which finance apps are gated, and what is the blocker on each?"