{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_8u5ksg79ya2b","handle":"axiom-perception-mcp","url":"https://wellknown.network/agents/axiom-perception-mcp","links":{"self":"https://wellknown.network/agents/axiom-perception-mcp/record.json","html":"https://wellknown.network/agents/axiom-perception-mcp","markdown":"https://wellknown.network/agents/axiom-perception-mcp/record.md","api":"https://wellknown.network/api/v1/agents/axiom-perception-mcp","status":"https://wellknown.network/api/v1/agents/axiom-perception-mcp/status","claim":"https://wellknown.network/agents/axiom-perception-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/axiom-perception-mcp/claim.json","badge":"https://wellknown.network/agents/axiom-perception-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/axiom-perception-mcp/history","tools":"https://wellknown.network/api/v1/agents/axiom-perception-mcp/tools"},"ard":{"identifier":"urn:air::server:axiom-perception-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"axiom-perception-mcp","summary":"Empirical memory for AI agents — patterns learned from real executions, not hand-written rules. Workflow checkpointing, failure knowledge base, multi-agent coordination. Zero API keys required.","description":"# axiom-perception-mcp\n\n**Persistent memory and pattern learning for AI agents.**\n\nClaude forgets how to use your computer between sessions. axiom-perception-mcp fixes that — it gives Claude a long-term memory for multi-step workflows so it never re-learns the same thing twice.\n\n```\nclaude: recall_pattern(\"post tweet\")\n→ \"Found pattern v3 (97% success rate, 42 executions):\n    1. Navigate to x.com\n    2. Click 'Post' in the left sidebar\n    3. ...\"\n```\n\nZero API keys. No setup. Just install and Claude starts remembering.\n\n---\n\n## Install\n\n```bash\n# Claude Desktop / Claude Code\nuvx axiom-perception-mcp\n```\n\nAdd to your MCP client config:\n```json\n{\n  \"mcpServers\": {\n    \"perception\": {\n      \"command\": \"uvx\",\n      \"args\": [\"axiom-perception-mcp\"]\n    }\n  }\n}\n```\n\n---\n\n## The problem it solves\n\nWhen Claude tries to do something in your browser — post a tweet, create a PR, fill a form — it often spends 5-10 minutes figuring it out through trial and error. Every session, from scratch.\n\naxiom-perception-mcp stores what worked. Next time, Claude skips straight to the answer.\n\n**Works alongside any automation tool**: Playwright MCP, Computer Use, browser tools. This MCP handles *what to do*, your automation tool handles *how to do it*.\n\n---\n\n## 8 tools\n\n| Tool | What it does |\n|------|-------------|\n| `recall_pattern(task, app?)` | Get the best known workflow **before** starting a task |\n| `save_pattern(task, steps, app, category)` | Save a workflow that worked |\n| `update_pattern(id, steps, reason?)` | Improve a pattern with a better approach |\n| `record_outcome(id, success, time_ms?)` | Track executions to build success rate |\n| `list_patterns(app?, category?)` | Browse all known workflows |\n| `search_patterns(query)` | Search across all patterns |\n| `export_pattern(id)` | Export as JSON to share with the community |\n| `fetch_community_patterns(app?)` | Import proven patterns from the shared database |\n\n---\n\n## Community patterns — no cold start\n\nOn first use, run `fetc…","publisher":null,"homepage":null,"repository":null,"version":"2.1.0","license":null,"protocols":["mcp"],"tags":["agent","ai-agent","automation","claude","learning","mcp","memory","patterns","playwright","workflow"],"pricing":null,"endpoints":[{"url":"pypi:axiom-perception-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"declared"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":1,"provenance":"declared"},{"slug":"automation.orchestration","name":"Agent Orchestration","confidence":0.905,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"}],"categories":["automation","data","infra","knowledge"],"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":"axiom-perception-mcp","registry":"pypi","observedAt":"2026-10-27T20:23:55.051Z","publishedAt":"2026-04-16T15:39:17.099396Z","latestVersion":"2.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"axiom-perception-mcp","url":"https://pypi.org/project/axiom-perception-mcp/","firstSeenAt":"2026-09-09T10:26:17.141Z","fetchedAt":"2026-10-27T20:22:41.521Z","normalizedAt":"2026-10-27T20:22:41.521Z"}]},"firstSeenAt":"2026-09-09T10:26:17.141Z","updatedAt":"2026-10-27T20:23:55.051Z"}