TA

Task402 Agent Evidence Tools

xyz.task402/x402-docs

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

Yes, your AI can use this right now.Answered a live MCP handshake in 460 ms with no sign-in needed and exposes 20 tools.

Connect it

Settings → Connectors → Add custom connector
URL: https://task402.xyz/mcp

20 tools, verified live

Pulled straight from the server with tools/list on 2026-10-17.
generate_pdf

Create a professionally formatted, paginated PDF from Markdown. Returns a short-lived download capability.

get_pdf_jobread-only

Read the status for a PDF job using its unguessable capability.

inspect_pdfread-only

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.

get_document_mapread-only

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.

search_documentread-only

Find exact normalized text matches in native PDF text (no OCR). Results and excerpts are bounded.

batch_search_documentread-only

Search up to 20 exact normalized-text queries in one bounded call. Useful when an agent needs several clauses or fields from one PDF.

prepare_document_contextread-only

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.

extract_document_fieldsread-only

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.

read_documentread-only

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.

verify_document_citationread-only

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.

compare_pdfsread-only

Compare page count and normalized native text between two separately authorized uploaded PDFs. Image-only and visual differences are not compared.

validate_pdf_textread-only

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.

render_pdf_page_regionread-only

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.

web_evidenceread-only

Fetch a public HTTPS page and return bounded citation-ready evidence.

inspect_openapiread-only

Inspect a caller-supplied OpenAPI JSON document without fetching remote references.

plan_api_requestread-only

Select an OpenAPI operation and generate a safe request plan without executing it.

diff_openapiread-only

Compare two caller-supplied OpenAPI JSON documents.

get_chain_balanceread-only

Read a native Base balance.

get_chain_transactionread-only

Read a Base transaction and receipt.

get_erc20_balanceread-only

Read one ERC-20 balance on Base.

Alternatives in Crypto & Web3

Compare →
Try “Notion”, “Stripe”, “create invoice”, “browser”