{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ukr66ybvxhv3","handle":"neruva-mcp-2","url":"https://wellknown.network/agents/neruva-mcp-2","links":{"self":"https://wellknown.network/agents/neruva-mcp-2/record.json","html":"https://wellknown.network/agents/neruva-mcp-2","markdown":"https://wellknown.network/agents/neruva-mcp-2/record.md","api":"https://wellknown.network/api/v1/agents/neruva-mcp-2","status":"https://wellknown.network/api/v1/agents/neruva-mcp-2/status","claim":"https://wellknown.network/agents/neruva-mcp-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/neruva-mcp-2/claim.json","badge":"https://wellknown.network/agents/neruva-mcp-2/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:neruva-mcp-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"neruva-mcp","summary":"Verified skills for AI agents. Find, install and run helper code that a program has checked on cases it never saw, and build your own: every skill ships the exact checker that proved it, so you can re-run the evidence yourself instead of taking our word for it. Free to read and install, no key and …","description":"# neruva-mcp \n \n**Verified skills for AI agents.** Do not replace your model. Give it proven capabilities. \n \nThe Python MCP server for [Neruva](https://neruva.io). \n \n## What this is for \n \nYour model gets some jobs wrong in the same way every time. A page that has to be landscape. A \nform field named by a tax agency rather than by its label. A chart the spreadsheet quietly \ndiscards. Telling it again does not help, because it writes the code fresh each time. \n \nA **skill** is that code, written once and proved correct by a program on cases it had never \nseen. Your agent calls the skill instead of writing its own, and gets the same result every time. \n \nMeasured on held-out cases, best of two samples, graded by an exact checker: \n \n| job | the model alone | with the skill | \n| --- | --- | --- | \n| Word document, portrait then landscape with a header and table | 25% | 100% | \n| PowerPoint combo chart on a secondary axis | 13% | 100% | \n| Fillable PDF form | 44% | 100% | \n| The real Canadian TD1 tax form | 19% | 94% | \n \nEvery number on [neruva.io/evidence](https://neruva.io/evidence/) names the run behind it, \nincluding the contexts where we measured, found the model already coped, and published nothing. \n \n## Install \n \n```bash \npip install neruva-mcp \n``` \n \nPoint your MCP host at it. Reading and installing skills need no key: \n \n```json \n{ \n  \"mcpServers\": { \n    \"neruva\": { \"command\": \"neruva-mcp\" } \n  } \n} \n``` \n \nAdd a key only to publish a skill, claim a name or post paid work: \n \n```json \n{ \n  \"mcpServers\": { \n    \"neruva\": { \"command\": \"neruva-mcp\", \"env\": { \"NERUVA_API_KEY\": \"nv_...\" } } \n  } \n} \n``` \n \n## Tools \n \n**Using a skill.** No key needed for any of these. \n \n| tool | what it does | \n| --- | --- | \n| `skill_search` | Find a verified skill before writing code for a task. | \n| `skill_get` | One skill: code, usage guide, evidence, checker, certificate. Pass `parts: [\"summary\"]` while deciding, which costs a few hundred tokens instead of thousands. |…","publisher":null,"homepage":"https://neruva.io/docs/","repository":null,"version":"0.69.2","license":"Proprietary -- (c) Clouthier Simulation Labs. For Neruva integr…","protocols":["mcp"],"tags":["mcp","model-context-protocol","neruva","agent-memory","agent-context","agentic-ai","knowledge-graph","graph-rag","rag","vector-database","claude-code","claude-agent-sdk","ai","llm"],"pricing":null,"endpoints":[{"url":"pypi:neruva-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"content.writing","name":"Writing & Editing","confidence":0.802,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.675,"provenance":"derived"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":0.638,"provenance":"derived"}],"categories":["content","data","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":"neruva-mcp","registry":"pypi","observedAt":"2026-09-10T07:21:52.226Z","publishedAt":"2026-09-05T15:37:58.621506Z","latestVersion":"0.69.2"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"neruva-mcp","url":"https://pypi.org/project/neruva-mcp/","firstSeenAt":"2026-09-10T07:21:19.703Z","fetchedAt":"2026-09-10T07:21:19.703Z","normalizedAt":"2026-09-10T07:21:19.703Z"}]},"firstSeenAt":"2026-09-10T07:21:19.703Z","updatedAt":"2026-09-10T07:21:52.226Z"}