{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_fmaqa4px9wzu","handle":"blop-mcp","url":"https://wellknown.network/agents/blop-mcp","links":{"self":"https://wellknown.network/agents/blop-mcp/record.json","html":"https://wellknown.network/agents/blop-mcp","markdown":"https://wellknown.network/agents/blop-mcp/record.md","api":"https://wellknown.network/api/v1/agents/blop-mcp","status":"https://wellknown.network/api/v1/agents/blop-mcp/status","claim":"https://wellknown.network/agents/blop-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/blop-mcp/claim.json","badge":"https://wellknown.network/agents/blop-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/blop-mcp/history","tools":"https://wellknown.network/api/v1/agents/blop-mcp/tools"},"ard":{"identifier":"urn:air::server:blop-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"blop-mcp","summary":"MCP-native release confidence control plane for web apps","description":"# blop — The MCP-Native Release Confidence Control Plane\n\nMost AI testing tools can click through pages. Teams still do not know whether they should ship.\n\n**blop** turns browser execution into **release decisions** by combining business-critical journey context, evidence-heavy QA runs, and risk governance in one MCP-native control plane.\n\nYou do not write test code. You ask in chat, then ship with auditable evidence, prioritized risk, and a clear go/no-go recommendation.\n\nCompatible MCP clients: **Cursor**, **Claude Code**, and other clients that support MCP tool/resource workflows.\n\n## Quick Navigation\n\n- [Product thesis](#product-thesis)\n- [What it actually does](#what-does-it-actually-do)\n- [Why blop vs generic AI testing agents](#why-blop-vs-generic-ai-testing-agents)\n- [Before you start](#before-you-start--what-youll-need)\n- [Install](#installation--step-by-step)\n- [Release packaging](#release-packaging)\n- [Configure and connect](#configure-and-connect-blop)\n- [Production setup](#production-setup-local-managed-stdio)\n- [5-minute quickstart](#your-first-mcp-native-run-in-5-minutes)\n- [Business-context QA scenarios](#real-world-testing-scenarios-for-b2b-saas)\n- [MCP resources + v2 surface](#mcp-resources--v2-surface-summary)\n- [Troubleshooting](#troubleshooting)\n- [Full tool reference](#full-tool-reference)\n\n---\n\n## Product thesis\n\n- **Core belief:** teams do not have a \"generate more tests\" problem; they have a **release confidence** problem.\n- **What competitors miss:** bug detection without business weighting creates noisy output and weak ship/no-ship decisions.\n- **What blop uniquely does:** connect context graphs, regression evidence, incident patterns, and telemetry into a single risk narrative that leaders can act on.\n\n---\n\n## What does it actually do?\n\n1. **Captures context** with inventory + graph resources agents can read cheaply\n2. **Discovers and records** business-critical flows from that context\n3. **Replays** flows asynchronously to catch regress…","publisher":null,"homepage":"https://github.com/n2400813g/blop-mcp/blob/main/README.md","repository":"https://github.com/n2400813g/blop-mcp/blob/main/README.md","version":"0.3.0","license":null,"protocols":["mcp"],"tags":["mcp","browser","automation","release","confidence","qa","playwright"],"pricing":null,"endpoints":[{"url":"pypi:blop-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"code.testing","name":"Testing","confidence":1,"provenance":"declared"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":1,"provenance":"declared"},{"slug":"communication.chat","name":"Team Chat","confidence":0.745,"provenance":"derived"}],"categories":["code","communication","infra"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"blop-mcp","registry":"pypi","observedAt":"2026-10-27T20:24:12.609Z","publishedAt":"2026-03-22T20:38:19.991718Z","latestVersion":"0.3.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"blop-mcp","url":"https://pypi.org/project/blop-mcp/","firstSeenAt":"2026-09-09T10:27:29.031Z","fetchedAt":"2026-10-27T20:23:32.582Z","normalizedAt":"2026-10-27T20:23:32.582Z"}]},"firstSeenAt":"2026-09-09T10:27:29.031Z","updatedAt":"2026-10-27T20:24:12.609Z"}