toolcall-linter is a local CLI linter designed for developers building LLM agents. It cross-checks tool calls found in agent transcripts against the schemas declared for those tools, helping catch inconsistencies and errors early. It supports MCP and is available as an open-source MIT-licensed Python package on GitHub.
toolcall-linter sits in PulseGate's Code review & quality category. It focuses on ensuring that tool calls made by AI agents in transcripts are consistent with their declared function schemas. It is built as an open-source project for developers. toolcall-linter is open source under the MIT license. toolcall-linter is available on the command line.
It is developed by Victorchatter, and it first shipped in 2026. The project is developed in the open on GitHub with 10 commits in the last 90 days. Among its 4 catalogued features are Schema Validation, Tool Call Checking, and Agent Transcript Analysis. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do