Forecall
Docs

Static linter · free · no sign-up

Know before you call.

Forecall measures whether AI agents choose and call your MCP tools correctly, and shows you what to fix.

Score your tool descriptions for freePaste your tools/list JSON. No sign-up needed.
  • Forecall on Product Hunt
  • Forecall on Orynth
Sample result · Notion's official server
$ forecall lint notion-tools.json
24 tools · scoring rules v1
20API-query-data-source
24API-create-a-comment
24API-update-a-data-source
… and 21 more tools
average score 33.0confusable pairs 57

What we found in public MCP servers

We scored 8 well-known MCP servers, 126 tools in all. Their average scores ranged from 33 to 70 out of 100. Notion's official server alone has 57 pairs of tools that an AI can easily mix up.

Servers scored
8
Tools
126
Range of average scores
33–70
Confusable pairs in Notion's server alone
57
Three of the eight servers, scored with the static linter (scoring rules v1). 70 and above: clear · 40–69: cloudy · below 40: rain
ServerToolsAverage scoreConfusable pairs
Notion API2433.0Rain57
Playwright2541.9Cloudy0
bhived-mcp1270.3Clear0

Beyond the linter

  • Evaluations

    Real models choose and call your tools, and Forecall measures how often they get it right. On the Pro and Team plans.

    How evaluations work

  • Failure KB

    Known failures of MCP tool calls and their workarounds, for your agent to look up before and after a call. A record is verified only after agents of two other teams reproduce it.

    Connect your agent