MCP servers tagged ci
123 live MCP servers tagged "ci", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with ci.
Flightcheck
Tries to break your MCP server before your users do. Runtime checks with spec citations, made for CI.
Stdio Purity
Fail CI when an MCP stdio server writes any non-JSON-RPC record to stdout during startup, probing, or cleanup.
Tool Safety Lab
Public-safe MCP-style tool safety lab with permission gates, approval boundaries, schemas, audit logs, and CI tests.
Skillbudget
Budget the always-loaded token cost of your AI agent context (CLAUDE.md, skills, Cursor rules) and fail CI when it bloats.
Oversight Lint Action
GitHub Action to lint your Storybook MCP components manifest in CI, reporting findings as GitHub annotations.
Manual CLI
Self-verifying repository operating manual: every claim about a repo is backed by an executable check, stamped fresh/stale/broken/blocked, and compiled into token-budgeted briefs…
Changeguard
MCP ChangeGuard product and proof surface; paid release-gate kit is not included
Galacticfederation
RepoTruth: CI that reads the repository, not just the diff. Signed-webhook verification, one audit core as CLI, MCP server and fleet dashboard. 147 tests.
Regression Lab
GitHub Action: catch MCP server releases that silently break agents (tool contract diff, lint, golden tests)
Toolscan
Cross-platform tool discovery beyond PATH: XDG + common install roots, bounded and truthful with fail-closed JSON. For agent harnesses, skill installers, MCP servers, CI drift che…
Toolstrict
Lint LLM tool/function-calling INPUT schemas for strictness - loose schemas cause hallucinated/invalid arguments. Flags no-required, open additionalProperties, or untyped properti…
Repotruth
RepoTruth: CI that reads the repository, not just the diff. Signed-webhook verification, one audit core as CLI, MCP server and fleet dashboard. 147 tests.
Tool Call Replay Harness
Offline replay and assertion harness for AI agent tool-call transcripts, fixtures, retries, budgets, JUnit reports, and CI gates.
Setup Grimoire
GitHub Action + shell installers for the grim CLI (setup.grimoire.rs)
Skill Scan Gate
CI gate for Claude Code skills and plugins: scans a skills or plugin repository for instruction-override text, exfiltration patterns, dangerous hook commands, unpinned MCP servers…
Covenant
Contract & breaking-change detector for MCP servers — semver for your interface. Snapshot tools/resources/prompts into a lockfile, diff in CI, fail on breaking changes. Single Rus…
Eval
CI-embeddable eval harness for MCP agents — scores the sequence of tool calls your agent makes, not just text output
MCPGuard
MCPGuard is the open-source CI gate for MCP servers — it tests protocol compliance, scans for security vulnerabilities, validates tool behavior, and benchmarks performance before…
Mcpcheck
Correctness checks for MCP servers — prompt-injection lint, contract drift, over-broad tools, dishonest annotations. Never calls a tool.
Gate
GitHub Action: MCP conformance gate - PR report, scenario coverage, compliance badge over the official MCP conformance runner
Woodpecker MCP
MCP server for Woodpecker CI: pipeline status, logs and guarded restart/cancel
Config Lint
Lint, security-check, and token-cost your Claude Desktop MCP config (claude_desktop_config.json). CI-friendly, zero deps. pip install mcp-config-lint
Lint
GitHub Action: validate MCP server cards (SEP-1649) and catch MCP context-window bloat in CI. Zero dependencies.