The library
Everything we index — ranked by what works, never by stars.
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
● works · ● untested / no effect · ● hurts — every rank is measured against a no-skill baseline
untested★2→untested★368→untested★0→untested★368→untested★1→untested★0→untested★0→untested★0→untested★15→untested★1→untested★0→untested★0→untested★10→untested★2→untested★0→untested★1→untested★3→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→untested★0→
Discover untested code paths and generate testsworkflowEngineeringL2
test-expander · Test suite expansion when round-trip generation and adversarial validation are needed.
Execute parallel workflows with convergence verificationworkflowEngineeringL3
wf-execute · Complex multi-phase workflows when barrier synchronization and per-phase label tracking are required.
Run phase-4 code review tracks in parallelworkflowEngineeringL3
forge-phase4-review · Stage-gate project reviews when distributed team consensus and blockers are tracked.
Multi-perspective code review with adversarial verificationworkflowEngineeringL3
wf-review · Post-workflow synthesis when parallel-phase outputs must be reconciled into actionable findings.
Benchmark code across 8 concurrent workersworkflowEngineeringL3
bench-s2-parallel · Model selection when parallel-agent latency and throughput baselines must be measured.
Score competing implementations adversariallyworkflowEngineeringL3
tooltuner-judge · Tool optimization when results must be ranked against a baseline and winner declared.
Debate code findings to consensusworkflowEngineeringL3
lens-debate · Code reviews where structural fit matters more than style, paired with expedited fix application.
Scan files for concerns with adversarial verificationworkflowEngineeringL3
review-files · Scanning a subset of files for a concrete concern (e.g., hardcoded secrets, missing validation).
Review TUI code across 5 quality dimensionsworkflowEngineeringL3
ratatui-tui-review · Systematic dimensional review of ratatui apps before release, catching architecture + safety drift.
Execute build chunks with auto-fix and structured feedbackworkflowEngineeringL3
session-orchestrate-build · Large features where chunked implementation avoids bloat + auto-escalation prevents silent failure.
Audit design-to-code gaps with verificationworkflowEngineeringProductL3
m1m8-gap-audit · Verifying that large real-time systems stay synchronized between intent (design) and implementation.
Detect and fix API specification driftworkflowEngineeringL3
api-contract-drift-detector · Catching API shape evolution that outruns documentation, automated on every release.
Cross-verify findings with independent skepticsworkflowEngineeringL3
adversarial_review · Quality gates where reducing false positives via skeptic consensus beats upfront filtering.
Remediate reference changes in parallelworkflowEngineeringL3
references-audit-remediate · Batching reference-fix decisions (from a prior classification gate) for parallel execution.
Ingest and verify candidate artifactsworkflowEngineeringL3
loop-c-ingestion · Validating backlog artifacts against live source before promoting to canon.
Execute top-level module-result workflowsworkflowEngineeringL3
module-result · Testing and exercising the module-result contract in the Workflow runtime.
Pipeline PRD through architecture to threat modelworkflowProductEngineeringL3
mishkan-init · Fast-tracking project bootstrap by starting research stages as soon as their upstream dependencies become available.
Access source code and documentation on GitHubmcp_serverEngineeringL2
gread · Equip agents to understand library source code and docs without web searches.
Install MCP servers across coding agentsmcp_serverEngineeringOpsL2
add-mcp · Bootstrap MCP setup across multiple agents uniformly without manual JSON editing.
Automate Azure infrastructure operationsmcp_serverOpsEngineeringL3
mcp · Automate Azure infrastructure tasks (deploy VMs, manage databases, configure storage) within agent workflows.
Manage GitLab workflows and CI/CDmcp_serverEngineeringL2
mcp-gitlab · Integrate GitLab workflows (CI/CD, code review, issue tracking) into agent-driven development pipelines.
Compress MCP tool descriptionsmcp_serverEngineeringL2
caveman-shrink · Reduce token cost of large MCP tool catalogs by 20-40% without changing tool semantics.
Build MCP tool explorer dashboardsmcp_serverEngineeringL2
client · Create browser-based MCP tool explorers and dashboards for non-technical users.
Bridge Genkit and MCP frameworksmcp_serverEngineeringL3
mcp · Use Genkit's multi-model orchestration with MCP tools as drop-in resource providers.
Connect local clients to remote MCPmcp_serverEngineeringL2
mcp-remote · Connect Claude Desktop or Cursor (stdio-only) to cloud-hosted MCP servers without client upgrade.
Search vectors with hybrid retrievalmcp_serverEngineeringDataL2
turbopuffer · Add semantic search to agent systems needing fast, scalable vector DB without managing infrastructure.
Discover and test MCP serversmcp_serverEngineeringL2
mcp-man · Discover, understand, and test MCP servers without reading GitHub READMEs or guessing parameters.
Expose MCP tools to LangChainmcp_serverEngineeringL2
mcp-adapters · Making MCP servers compatible with LangChain.js and LangGraph.js agents
Coordinate multiple AI agentsmcp_serverEngineeringL2
mcp · When you need mcp capabilities in your MCP stack
Discover and test MCP servers CLImcp_serverEngineeringL2
mcp-inspector · When you need mcp-inspector capabilities in your MCP stack
Coordinate AI agents via UTCPmcp_serverEngineeringL2
mcp · When you need mcp capabilities in your MCP stack
Manage Kubernetes cluster operationsmcp_serverOpsEngineeringL3
mcp-server-kubernetes · When you need mcp-server-kubernetes capabilities in your MCP stack
Containerize apps with AI optimizationmcp_serverEngineeringL4
containerization-assist-mcp · AI-assisted containerization with policy-driven generation, security scanning, and K8s manifest generation.
Render interactive web UI from MCPmcp_serverEngineeringL4
server · Building interactive MCP-driven web UIs with multi-language SDK support (TS, Ruby, Python).
Build SAP UI5 applications with AImcp_serverEngineeringL3
mcp-server · Scaffolding new UI5 apps and guiding AI agents through UI5 best practices and linting.
Wrap OpenAPI or GraphQL as MCPmcp_serverEngineeringL3
mcp-server · Wrapping existing OpenAPI/GraphQL APIs as MCP servers without reimplementing tools.
Audit agent actions with distributed tracingmcp_serverEngineeringLegalL4
agent · Multi-framework agent provenance tracking with cross-agent audit and commerce closure evidence.
Build MCP servers in TypeScriptmcp_serverEngineeringL4
mcp-framework · Rapid scaffolding of MCP servers without boilerplate.
Query Dynatrace monitoring metricsmcp_serverEngineeringOpsL2
dynatrace-mcp-server · Real-time observability integration—querying metrics, entities, and incident data from Dynatrace.
Build MCP servers with NestJSmcp_serverEngineeringL4
mcp-nest · Building MCP servers within existing NestJS applications with DI and module patterns.
Initialize Neon databases in editormcp_serverEngineeringL2
neon-init · Setting up Neon database development in your editor without manual API key copy/paste.
Build MCP servers without boilerplatemcp_serverEngineeringL3
fastmcp · Building production MCP servers without boilerplate from the official SDK.
Query LaunchDarkly feature flagsmcp_serverProductEngineeringL2
mcp-server · Letting AI agents query and evaluate LaunchDarkly flags without CLI or API docs.
Automate iOS builds without Xcode UImcp_serverEngineeringL3
xcodebuildmcp · Automating iOS/macOS CI/CD without stepping through Xcode UI.
Manage Argo CD deployments with AImcp_serverEngineeringOpsL3
argocd-mcp · Enabling AI agents to check and sync Argo CD applications without kubectl access.
Validate MCP servers in CImcp_serverEngineeringL3
mcp-probe · Proving in CI that your MCP server actually works on real tool calls, not just schemas.
Test MCP servers end-to-endmcp_serverEngineeringL3
sdk · Validating MCP server functionality and performance across unit + integration + eval layers.
Orchestrate multi-step AI agent workflowsmcp_serverEngineeringOpsL3
agentation-mcp · Orchestrating complex agentic workflows from within an MCP client.
Bootstrap TanStack Start projects instantlymcp_serverEngineeringL2
mcp-tanstack-start · Bootstrapping TanStack Start projects from AI without typing CLI commands.
Run analytical queries without SQL editormcp_serverDataEngineeringL2
clickhouse · Letting AI agents run analytical queries on ClickHouse without SQL editor.