Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "code_analyze" and "code_get_findings"
⟨222 unchanged words⟩ "scan_test_files":{"default":false,"description":"IncludeOldertestspellingfilesofintests=\"include\",codehonouredqualitywhenandtestscredentialisscannotresults.set.TestPreferfilestests.","type":"boolean"},"tests":{"default":"exclude","description":"FindingsareinexcludedTESTbyfilesdefault(*_test.go,totest/,reducetests/,falsespec/,positives__tests__/,(e.g.testdata/,test*.test.ts,credit*.spec.js,card*Test.java,numbers*Tests.cs,mocktest_*.py,credentialsconftest.py, *_spec.rb and the like).Set\"exclude\",tothetruedefault,ifleavesyouthemneedouttoofauditcode_quality_summary and security_summary and counts them in tests_excluded; \"include\" adds them, each marked test:code.true; \"only\" returns just them. They are kept, not deleted: a credential committed in a test fixture is still a real credential, and include reaches it.","enum":["exclude","include","only"],"type":"booleanstring"}},"required":["repository"],"type":"object"}
⟨189 unchanged words⟩ "scan_test_files":{"default":false,"description":"IncludeOlderfindingsspellingfromoftesttests=\"include\",files.honouredBywhendefaultteststestisfilesnotareset.excluded.Prefer tests.","type":"boolean"},"severity":{ ⟨6 unchanged words⟩ ,"enum":["error","warning","info"],"type":"string"},"tests":{"default":"exclude","description":"Findings in TEST files (*_test.go, test/, tests/, spec/, __tests__/, testdata/, *.test.ts, *.spec.js, *Test.java, *Tests.cs, test_*.py, conftest.py, *_spec.rb and the like). \"exclude\", the default, leaves them out of findings and total_findings and counts them in tests_excluded; \"include\" adds them, each marked test: true; \"only\" returns just them. They are kept, not deleted: a credential committed in a test fixture is still a real credential, and include reaches it.","enum":["exclude","include","only
Changed the definition of "code_analyze", "code_get_findings" and "code_search"
⟨8 unchanged words⟩ , tech stack, code quality findings, andcredentialsecret scanning. Use as your first call to understand any remote public codebase. This is the tool that scans for LEAKED CREDENTIALS: security_summary is a dedicated secret and credential scanner covering API keys, access tokens, private keys and connection strings, each with a file, a line and a confidence grade. Prefer it over grepping for key prefixes with code_search — a pattern search only finds what you thought to spell, and finds nothing at all in the repositories where you guessed wrong. Supports language filtering and path scoping (for ⟨26 unchanged words⟩
⟨67 unchanged words⟩ Certificate recorded, valid to 2026-12-02
Authorization not required
First tool surface recorded: 7 tools (server version 1.0.0)
Showing the latest 5 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨29 unchanged words⟩ strings, comments). Dependency/build directories excluded by default. Searching for leaked secrets? Call code_analyze instead and read security_summary — it runs a real secret and credential scanner over the whole repository, where searching for key prefixes like "sk-", "ghp_" or "AIza" only matches the spellings you happened to think of.