{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_zwz9wxpuhn78","handle":"sentra-mcp","url":"https://wellknown.network/agents/sentra-mcp","links":{"self":"https://wellknown.network/agents/sentra-mcp/record.json","html":"https://wellknown.network/agents/sentra-mcp","markdown":"https://wellknown.network/agents/sentra-mcp/record.md","api":"https://wellknown.network/api/v1/agents/sentra-mcp","status":"https://wellknown.network/api/v1/agents/sentra-mcp/status","claim":"https://wellknown.network/agents/sentra-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/sentra-mcp/claim.json","badge":"https://wellknown.network/agents/sentra-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/sentra-mcp/history","tools":"https://wellknown.network/api/v1/agents/sentra-mcp/tools"},"ard":{"identifier":"urn:air::server:sentra-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"sentra-mcp","summary":"Sentra — local-first MCP server for mock exam generation","description":"# Sentra — mock exams from your PDFs (free, open-source MCP server)\n\nSentra turns lecture PDFs and past exams into realistic mock exams with\nanswer keys. It runs on your machine, costs nothing, and works with any\nMCP-compatible AI agent (OpenCode, Claude Code, Cursor, VS Code, Gemini CLI).\n\nYour agent does the thinking; Sentra does the reading, the analysis prep,\nand the file saving. Sentra itself makes no model calls.\n\nBilingual site + docs: [`landing/`](landing/) (English / Egyptian Arabic).\n\n## Fastest start\n\n1. Copy this repo link: `https://github.com/mo22zy2/Sentra-MCP`\n2. In your AI agent, paste it and say: `download and run this mcp`\n3. Restart your agent so the sentra tools appear.\n4. Drop lecture PDFs into `lectures/` and past exams into `past_exams/`.\n5. Say: `run the sentra pipeline` — the agent follows the prompts in order\n   (`extract_text → knowledge_base → professor_dna → exam_targets → predicted_exam`)\n   and saves each `.md` under `output/`. No forms, no schema — the prompts\n   define the structure. Or say: `make me 2 exams using the sentra mcp`.\n\nNot on OpenCode? `uvx sentra-mcp init --agent <claude|cursor|vscode|gemini>`\nwrites the right config for your agent. Every agent uses the same local\n`lectures/`, `past_exams/`, `output/` folders.\n\n## Prefer the terminal?\n\nInstall `uv` once (Windows: `winget install -e --id astral-sh.uv`,\notherwise: `pip install uv`), then:\n\n```bash\nuvx sentra-mcp init\n```\n\n`init` creates your course folder, connects your agent (backing up its\nconfig first), and tells you where to drop PDFs. Then ask your agent:\n\n- \"Analyze the previous exams and summarize the professor's question patterns.\"\n- \"Generate a two-hour Operating Systems mock exam with an answer key.\"\n\nYou get `output/<name>_exam.md` + `output/<name>_answers.md`, saved locally.\n\n## Your folders\n\n```\n<the folder you opened in your agent>/\n├── lectures/     # lecture PDFs (auto-created)\n├── past_exams/   # previous exam PDFs (auto-created)\n└── output/       # gene…","publisher":{"name":"mo22zy2","url":null},"homepage":"https://github.com/mo22zy2/Sentra-MCP","repository":"https://github.com/mo22zy2/Sentra-MCP","version":"1.1.0","license":"MIT","protocols":["mcp"],"tags":["education","mcp","mock-exam","opencode","study"],"pricing":null,"endpoints":[{"url":"pypi:sentra-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.779,"provenance":"derived"}],"categories":["dev"],"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":"sentra-mcp","registry":"pypi","observedAt":"2026-10-24T18:29:05.587Z","publishedAt":"2026-10-12T18:08:29.957805Z","latestVersion":"1.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"sentra-mcp","url":"https://pypi.org/project/sentra-mcp/","firstSeenAt":"2026-10-12T14:25:46.417Z","fetchedAt":"2026-10-24T18:28:18.884Z","normalizedAt":"2026-10-24T18:28:18.884Z"}]},"firstSeenAt":"2026-10-12T14:25:46.417Z","updatedAt":"2026-10-24T18:29:05.587Z"}