# Task402 Agent Evidence Tools

> Paid evidence tools for PDFs, public webpages, OpenAPI contracts, and Base chain data for AI agents.

- name: xyz.task402/x402-docs
- version: 0.3.2
- connection class: unknown (unknown)
- trust: 67/100 flags: unreachable
- quality: 86/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/xyz.task402%2Fx402-docs
- tools: https://api.protogrid.dev/v1/servers/xyz.task402%2Fx402-docs/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "x402-docs": {
      "type": "http",
      "url": "https://task402.xyz/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 5
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website -unreachable(3 failures) +updated-8d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 86/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 20 of 20 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 4,549 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 30 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 20, about 4,549 tokens to load them all
- tool set hash: 39cb8fb0e5718537cdc2c8bb4c2484d1
- tools last changed: 2026-10-12T14:56:51.458Z
- badge: [![protogrid quality](https://protogrid.dev/badge/xyz.task402/x402-docs.svg)](https://protogrid.dev/servers/xyz.task402/x402-docs)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-12 `get_erc20_balance` changed (inputSchema, outputSchema, annotations)
- 2026-10-12 `get_chain_transaction` changed (inputSchema, outputSchema, annotations)
- 2026-10-12 `get_chain_balance` changed (inputSchema, outputSchema, annotations)
- 2026-10-12 `diff_openapi` changed (inputSchema, outputSchema, annotations)
- 2026-10-12 `plan_api_request` changed (inputSchema, outputSchema, annotations)
- 2026-10-12 `inspect_openapi` changed (inputSchema, outputSchema, annotations)
- 2026-10-12 `web_evidence` changed (inputSchema, outputSchema, annotations)
- 2026-10-12 `render_pdf_page_region` changed (inputSchema, outputSchema, annotations)
- 2026-10-12 `validate_pdf_text` changed (inputSchema, outputSchema, annotations)
- 2026-10-12 `compare_pdfs` changed (inputSchema, outputSchema, annotations)

Full history: https://api.protogrid.dev/v1/servers/xyz.task402%2Fx402-docs/changes

## Remotes

- https://task402.xyz/mcp (streamable-http, auth none, reachable false, uptime30d 0.8787879)

## Packages

_none_

## Tools (20)

- `batch_search_document`: Search up to 20 exact normalized-text queries in one bounded call. Useful when an agent needs several clauses or fields from one PDF.
- `compare_pdfs`: Compare page count and normalized native text between two separately authorized uploaded PDFs. Image-only and visual differences are not compared.
- `diff_openapi`: Compare two caller-supplied OpenAPI JSON documents.
- `extract_document_fields`: Extract caller-supplied literal labels and adjacent native-text values with page and block evidence. Missing labels return null; no semantic extraction or OCR is performed.
- `generate_pdf`: Create a professionally formatted, paginated PDF from Markdown. Returns a short-lived download capability.
- `get_chain_balance`: Read a native Base balance.
- `get_chain_transaction`: Read a Base transaction and receipt.
- `get_document_map`: Return page labels, sizes, native-text previews, bookmarks, and sparse-text warnings. Set page to include up to 500 positioned text blocks for that page.
- `get_erc20_balance`: Read one ERC-20 balance on Base.
- `get_pdf_job`: Read the status for a PDF job using its unguessable capability.
- `inspect_openapi`: Inspect a caller-supplied OpenAPI JSON document without fetching remote references.
- `inspect_pdf`: Inspect a previously uploaded PDF using its document capability. Upload binary PDFs through POST /v1/documents; persist both the returned capability and recovery key securely.
- `plan_api_request`: Select an OpenAPI operation and generate a safe request plan without executing it.
- `prepare_document_context`: Rank native-text pages for a question and return a bounded context pack with page, block, and excerpt evidence. No model call or OCR is used.
- `read_document`: Read extractable native text from up to 10 selected pages. Output is limited to 32,000 characters; scanned pages need OCR, which is not provided.
- `render_pdf_page_region`: Render one authorized PDF page crop as PNG. x/y/width/height are normalized 0-1 page fractions; output is bounded to four million pixels.
- `search_document`: Find exact normalized text matches in native PDF text (no OCR). Results and excerpts are bounded.
- `validate_pdf_text`: Check that the PDF parses, has an optional expected page count, and contains required text. This does not perform PDF/A, signature, visual, or OCR validation.
- `verify_document_citation`: Check that a quote of 5 to 500 characters appears on the stated page in extracted native text. This does not establish truth or visual reading order.
- `web_evidence`: Fetch a public HTTPS page and return bounded citation-ready evidence.