{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_yvp7rnjfcqgd","handle":"pdfproof-mcp","url":"https://wellknown.network/agents/pdfproof-mcp","links":{"self":"https://wellknown.network/agents/pdfproof-mcp/record.json","html":"https://wellknown.network/agents/pdfproof-mcp","markdown":"https://wellknown.network/agents/pdfproof-mcp/record.md","api":"https://wellknown.network/api/v1/agents/pdfproof-mcp","status":"https://wellknown.network/api/v1/agents/pdfproof-mcp/status","claim":"https://wellknown.network/agents/pdfproof-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/pdfproof-mcp/claim.json","badge":"https://wellknown.network/agents/pdfproof-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/pdfproof-mcp/history","tools":"https://wellknown.network/api/v1/agents/pdfproof-mcp/tools"},"ard":{"identifier":"urn:air::server:pdfproof-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"pdfproof-mcp","summary":"Deterministic PDF document validation with traceable evidence.","description":"# pdfproof-mcp\n\n`pdfproof-mcp` is a framework-agnostic MCP server and Python engine for validating\nstructured JSON, Excel, or CSV test data against PDF documents. It resolves records through\nan ordered, configurable hierarchy and returns deterministic evidence, structured\nresults, and an HTML report.\n\nThe published distribution is named `pdfproof-mcp`; its Python import package is\n`pdfproof`.\n\nThe project is intentionally not a general PDF-to-Excel converter, browser automation\ntool, or LLM-based validation system.\n\n## Current status\n\nThe deterministic core and MCP integration are implemented. The approved architecture and\nimplementation sequence are in [PLAN.md](PLAN.md).\n\n## Core guarantee\n\nEach locator narrows only the candidates left by the preceding locator. The engine never\nsearches an expected field across the entire document after a record has been resolved,\nand never silently selects among ambiguous candidates.\n\n## Test-data formats\n\nJSON, multi-sheet Excel, and simple tabular CSV inputs normalize into the same test suite.\nEach user-defined `record_id` links its locators and validations, but is never an implicit PDF\nsearch key. See [the test-data schema](docs/test-data-schema.md) for the JSON example, Excel\nsheet design, CSV guidance, and the locator-versus-validation distinction. Canonical fields use\nstable machine keys with optional report labels; financial values use `Decimal` precision.\n\n## Usage modes\n\nFor batch testing, pass `test_data_path` pointing to JSON, Excel, or CSV. For interactive use,\nan AI host/client can convert a user request into direct structured `test_data` for the same\n`validate_document` tool. Both paths use one canonical model and one deterministic validation\nengine; the server does not parse natural language. See [MCP usage](docs/mcp-usage.md).\n\n## MCP server\n\nStart the stdio server from `C:\\pdfproof-mcp`:\n\n```text\n.venv\\Scripts\\python.exe -m pdfproof.server\n```\n\nThe primary `validate_document` tool accepts exactly one of `test_da…","publisher":{"name":"pdfproof-mcp contributors","url":null},"homepage":null,"repository":null,"version":"0.2.0","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:pdfproof-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","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"infra.browser-automation","name":"Browser Automation","confidence":0.859,"provenance":"derived"},{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":0.733,"provenance":"derived"}],"categories":["documents","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":"pdfproof-mcp","registry":"pypi","observedAt":"2026-11-09T23:25:33.571Z","publishedAt":"2026-09-02T13:06:49.156920Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"pdfproof-mcp","url":"https://pypi.org/project/pdfproof-mcp/","firstSeenAt":"2026-09-10T09:25:54.831Z","fetchedAt":"2026-11-09T23:24:50.498Z","normalizedAt":"2026-11-09T23:24:50.498Z"}]},"firstSeenAt":"2026-09-10T09:25:54.831Z","updatedAt":"2026-11-09T23:25:33.571Z"}