# Task402 Agent Evidence Tools (remote · task402.xyz)

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

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `task402.xyz`: 69/100 (this document), [markdown](https://verifymcp.io/servers/xyz-task402-x402-docs/task402.md), [page](https://verifymcp.io/servers/xyz-task402-x402-docs/task402)

## Channel facts

- Endpoint: `https://task402.xyz/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1842 tokens (~92/item across 20 items; 20 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 20 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 20 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Task402 Agent Evidence Tools MCP server?

Task402 Agent Evidence Tools is a hosted endpoint at https://task402.xyz/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http xyz-task402-x402-docs 'https://task402.xyz/mcp'
```

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.xyz-task402-x402-docs]
url = "https://task402.xyz/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "xyz-task402-x402-docs": {
      "type": "remote",
      "url": "https://task402.xyz/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add xyz-task402-x402-docs --url 'https://task402.xyz/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  xyz-task402-x402-docs:
    url: "https://task402.xyz/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "xyz-task402-x402-docs": {
      "Transport": "http",
      "Url": "https://task402.xyz/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add xyz-task402-x402-docs -t streamable-http -u 'https://task402.xyz/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-16 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 67, +7)

- [functional regression] Schema quality: 59 → 92
- [functional improvement] Tool coverage: 0% → 100%
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Tool “batch_search_document” now declares an output schema
- [functional improvement] Tool “compare_pdfs” now declares an output schema
- [functional improvement] Tool “diff_openapi” now declares an output schema
- [functional improvement] Tool “extract_document_fields” now declares an output schema
- [functional improvement] Tool “generate_pdf” now declares an output schema
- [functional improvement] Tool “get_chain_balance” now declares an output schema
- [functional improvement] Tool “get_chain_transaction” now declares an output schema
- [functional improvement] Tool “get_document_map” now declares an output schema
- [functional improvement] Tool “get_erc20_balance” now declares an output schema
- [functional improvement] Tool “get_pdf_job” now declares an output schema
- [functional improvement] Tool “inspect_openapi” now declares an output schema
- [functional improvement] Tool “inspect_pdf” now declares an output schema
- [functional improvement] Tool “plan_api_request” now declares an output schema
- [functional improvement] Tool “prepare_document_context” now declares an output schema
- [functional improvement] Tool “read_document” now declares an output schema
- [functional improvement] Tool “render_pdf_page_region” now declares an output schema
- [functional improvement] Tool “search_document” now declares an output schema
- [functional improvement] Tool “validate_pdf_text” now declares an output schema
- [functional improvement] Tool “verify_document_citation” now declares an output schema
- [functional improvement] Tool “web_evidence” now declares an output schema
- [functional] First check of Tool coverage: 100
- [functional] Schema quality: fair → good
- [functional] Server version: 0.3.0 → 0.3.2
- [cosmetic] “batch_search_document” reworded the description of “capability”
- [cosmetic] “batch_search_document” reworded the description of “document_id”
- [cosmetic] “batch_search_document” reworded the description of “limit”
- [cosmetic] “batch_search_document” reworded the description of “page”
- [cosmetic] “batch_search_document” reworded the description of “queries”
- [cosmetic] “compare_pdfs” reworded the description of “left_capability”
- [cosmetic] “compare_pdfs” reworded the description of “left_document_id”
- [cosmetic] “compare_pdfs” reworded the description of “right_capability”
- [cosmetic] “compare_pdfs” reworded the description of “right_document_id”
- [cosmetic] “diff_openapi” reworded the description of “after”
- [cosmetic] “diff_openapi” reworded the description of “before”
- [cosmetic] “diff_openapi” reworded the description of “idempotency_key”
- [cosmetic] “extract_document_fields” reworded the description of “capability”
- [cosmetic] “extract_document_fields” reworded the description of “document_id”
- [cosmetic] “extract_document_fields” reworded the description of “fields”
- [cosmetic] “generate_pdf” reworded the description of “idempotency_key”
- [cosmetic] “generate_pdf” reworded the description of “markdown”
- [cosmetic] “generate_pdf” reworded the description of “title”
- [cosmetic] “get_chain_balance” reworded the description of “address”
- [cosmetic] “get_chain_balance” reworded the description of “block”
- [cosmetic] “get_chain_balance” reworded the description of “idempotency_key”
- [cosmetic] “get_chain_balance” reworded the description of “network”
- [cosmetic] “get_chain_transaction” reworded the description of “idempotency_key”
- [cosmetic] “get_chain_transaction” reworded the description of “network”
- [cosmetic] “get_chain_transaction” reworded the description of “tx_hash”
- [cosmetic] “get_document_map” reworded the description of “capability”
- [cosmetic] “get_document_map” reworded the description of “document_id”
- [cosmetic] “get_document_map” reworded the description of “page”
- [cosmetic] “get_erc20_balance” reworded the description of “address”
- [cosmetic] “get_erc20_balance” reworded the description of “block”
- [cosmetic] “get_erc20_balance” reworded the description of “idempotency_key”
- [cosmetic] “get_erc20_balance” reworded the description of “network”
- [cosmetic] “get_erc20_balance” reworded the description of “token”
- [cosmetic] “get_pdf_job” reworded the description of “capability”
- [cosmetic] “get_pdf_job” reworded the description of “job_id”
- [cosmetic] “inspect_openapi” reworded the description of “idempotency_key”
- [cosmetic] “inspect_openapi” reworded the description of “spec”
- [cosmetic] “inspect_pdf” reworded the description of “capability”
- [cosmetic] “inspect_pdf” reworded the description of “document_id”
- [cosmetic] “plan_api_request” reworded the description of “idempotency_key”
- [cosmetic] “plan_api_request” reworded the description of “method”
- [cosmetic] “plan_api_request” reworded the description of “operation_id”
- [cosmetic] “plan_api_request” reworded the description of “path”
- [cosmetic] “plan_api_request” reworded the description of “spec”
- [cosmetic] “prepare_document_context” reworded the description of “capability”
- [cosmetic] “prepare_document_context” reworded the description of “document_id”
- [cosmetic] “prepare_document_context” reworded the description of “max_chars”
- [cosmetic] “prepare_document_context” reworded the description of “pages”
- [cosmetic] “prepare_document_context” reworded the description of “query”
- [cosmetic] “read_document” reworded the description of “capability”
- [cosmetic] “read_document” reworded the description of “document_id”
- [cosmetic] “read_document” reworded the description of “pages”
- [cosmetic] “render_pdf_page_region” reworded the description of “capability”
- [cosmetic] “render_pdf_page_region” reworded the description of “document_id”
- [cosmetic] “render_pdf_page_region” reworded the description of “height”
- [cosmetic] “render_pdf_page_region” reworded the description of “page”
- [cosmetic] “render_pdf_page_region” reworded the description of “scale”
- [cosmetic] “render_pdf_page_region” reworded the description of “width”
- [cosmetic] “render_pdf_page_region” reworded the description of “x”
- [cosmetic] “render_pdf_page_region” reworded the description of “y”
- [cosmetic] “search_document” reworded the description of “capability”
- [cosmetic] “search_document” reworded the description of “document_id”
- [cosmetic] “search_document” reworded the description of “limit”
- [cosmetic] “search_document” reworded the description of “page”
- [cosmetic] “search_document” reworded the description of “query”
- [cosmetic] “validate_pdf_text” reworded the description of “capability”
- [cosmetic] “validate_pdf_text” reworded the description of “document_id”
- [cosmetic] “validate_pdf_text” reworded the description of “page_count”
- [cosmetic] “validate_pdf_text” reworded the description of “required_text”
- [cosmetic] “verify_document_citation” reworded the description of “capability”
- [cosmetic] “verify_document_citation” reworded the description of “document_id”
- [cosmetic] “verify_document_citation” reworded the description of “page”
- [cosmetic] “verify_document_citation” reworded the description of “quote”
- [cosmetic] “web_evidence” reworded the description of “idempotency_key”
- [cosmetic] “web_evidence” reworded the description of “max_chars”
- [cosmetic] “web_evidence” reworded the description of “query”
- [cosmetic] “web_evidence” reworded the description of “url”

### 2026-10-11 (score 60)

First indexed and scored.

## MCP tools (20)

### `generate_pdf` (~75 tokens)

Generate PDF

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

Input parameters:

- `idempotency_key` (string, required): Stable key used to make a paid retry idempotent.
- `markdown` (string, required): Markdown content to paginate into the PDF.
- `title` (string, required): Human-readable title for the generated PDF.

Output parameters:

- `accepts` (array)
- `artifactBytes` (integer)
- `capability` (string)
- `createdAt` (string)
- `downloadUrl` (string)
- `error`
- `errorCode` (string)
- `expiresAt` (string)
- `extensions`
- `jobId` (string)
- `resource`
- `resumed` (boolean)
- `settlement`
- `state` (string)
- `statusUrl` (string)
- `title` (string)
- `x402Version` (number)

### `get_pdf_job` (~51 tokens)

Get PDF job status

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

Input parameters:

- `capability` (string, required): Short-lived capability returned by generate_pdf.
- `job_id` (string, required): Job UUID returned by generate_pdf.

Output parameters:

- `accepts` (array)
- `artifactBytes` (integer)
- `capability` (string)
- `createdAt` (string)
- `downloadUrl` (string)
- `error`
- `errorCode` (string)
- `expiresAt` (string)
- `extensions`
- `jobId` (string)
- `resource`
- `resumed` (boolean)
- `settlement`
- `state` (string)
- `statusUrl` (string)
- `title` (string)
- `x402Version` (number)

### `inspect_pdf` (~73 tokens)

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.

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.

Output parameters:

- `accepts` (array)
- `attachments` (array)
- `bookmarks` (array)
- `byteLength` (integer)
- `contentHash` (string)
- `createdAt` (string)
- `documentId` (string)
- `error`
- `expiresAt` (string)
- `extensions`
- `fileName` (string)
- `formFields` (array)
- `metadata`
- `operations` (array)
- `pageCount` (integer)
- `resource`
- `warnings` (array)
- `x402Version` (number)

### `get_document_map` (~88 tokens)

Get PDF page 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.

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.
- `page` (integer): Optional 1-based page number.

Output parameters:

- `accepts` (array)
- `bookmarks` (array)
- `documentId` (string)
- `error`
- `extensions`
- `pageCount` (integer)
- `pages` (array)
- `resource`
- `warnings` (array)
- `x402Version` (number)

### `search_document` (~100 tokens)

Search PDF text

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

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.
- `limit` (integer): Maximum number of matches to return.
- `page` (integer): Optional 1-based page filter.
- `query` (string, required): Exact or normalized text to find.

Output parameters:

- `accepts` (array)
- `documentId` (string)
- `error`
- `extensions`
- `hits` (array)
- `query` (string)
- `resource`
- `totalMatches` (integer)
- `truncated` (boolean)
- `x402Version` (number)

### `batch_search_document` (~109 tokens)

Batch search PDF text

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

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.
- `limit` (integer): Maximum matches per query.
- `page` (integer): Optional 1-based page filter.
- `queries` (array, required): One to twenty exact or normalized text queries.

Output parameters:

- `accepts` (array)
- `documentId` (string)
- `error`
- `extensions`
- `resource`
- `results` (array)
- `x402Version` (number)

### `prepare_document_context` (~113 tokens)

Prepare cited PDF 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.

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.
- `max_chars` (integer): Maximum context characters.
- `pages` (array): Optional 1-based pages to search.
- `query` (string, required): Question or terms used for deterministic page ranking.

Output parameters:

- `accepts` (array)
- `documentId` (string)
- `error`
- `evidence` (array)
- `extensions`
- `maxChars` (integer)
- `method` (string)
- `omittedPages` (array)
- `pages` (array)
- `query` (string)
- `resource`
- `selectedPages` (array)
- `text` (string)
- `truncated` (boolean)
- `warning` (string)
- `x402Version` (number)

### `extract_document_fields` (~88 tokens)

Extract labeled PDF 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.

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.
- `fields` (array, required): One to twenty literal labels to extract.

Output parameters:

- `accepts` (array)
- `documentId` (string)
- `error`
- `extensions`
- `fields` (array)
- `resource`
- `warning` (string)
- `x402Version` (number)

### `read_document` (~92 tokens)

Read PDF pages

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.

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.
- `pages` (array, required): One to ten 1-based page numbers to read.

Output parameters:

- `accepts` (array)
- `documentId` (string)
- `error`
- `extensions`
- `pages` (array)
- `resource`
- `truncated` (boolean)
- `x402Version` (number)

### `verify_document_citation` (~103 tokens)

Verify PDF text 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.

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.
- `page` (integer, required): 1-based page containing the quote.
- `quote` (string, required): Quote to verify in native PDF text.

Output parameters:

- `accepts` (array)
- `documentId` (string)
- `error`
- `evidence` (array)
- `extensions`
- `method` (string)
- `page` (integer)
- `pageLabel` (string)
- `pageTextOffset` (integer)
- `quote` (string)
- `reason` (string)
- `resource`
- `verified` (boolean)
- `warning` (string)
- `x402Version` (number)

### `compare_pdfs` (~88 tokens)

Compare PDFs

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

Input parameters:

- `left_capability` (string, required): Capability for the earlier PDF.
- `left_document_id` (string, required): UUID of the earlier PDF.
- `right_capability` (string, required): Capability for the later PDF.
- `right_document_id` (string, required): UUID of the later PDF.

Output parameters:

- `accepts` (array)
- `changedPageCount` (integer)
- `changedPages` (array)
- `error`
- `extensions`
- `identicalBytes` (boolean)
- `identicalExtractedPageText` (boolean)
- `left`
- `method` (string)
- `resource`
- `right`
- `truncated` (boolean)
- `warning` (string)
- `x402Version` (number)

### `validate_pdf_text` (~103 tokens)

Validate PDF text expectations

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.

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.
- `page_count` (integer): Expected number of pages.
- `required_text` (array): Literal text strings that must be present.

Output parameters:

- `accepts` (array)
- `checks` (array)
- `documentId` (string)
- `error`
- `extensions`
- `resource`
- `valid` (boolean)
- `warnings` (array)
- `x402Version` (number)

### `render_pdf_page_region` (~145 tokens)

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.

Input parameters:

- `capability` (string, required): Document capability returned by POST /v1/documents.
- `document_id` (string, required): UUID returned by POST /v1/documents.
- `height` (number, required): Normalized crop height.
- `page` (integer, required): 1-based page to render.
- `scale` (number): Render scale multiplier.
- `width` (number, required): Normalized crop width.
- `x` (number, required): Normalized left crop coordinate.
- `y` (number, required): Normalized top crop coordinate.

Output parameters:

- `accepts` (array)
- `bytes` (integer)
- `contentType` (string)
- `documentId` (string)
- `error`
- `extensions`
- `page` (integer)
- `resource`
- `x402Version` (number)

### `web_evidence` (~81 tokens)

Web evidence

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

Input parameters:

- `idempotency_key` (string, required): Stable key used to make a paid retry idempotent.
- `max_chars` (integer): Maximum characters to return.
- `query` (string): Optional phrase to locate in the page.
- `url` (string, required): Public HTTPS page URL to fetch.

Output parameters:

- `accepts` (array)
- `contentType` (string)
- `description`
- `error`
- `extensions`
- `extraction` (string)
- `fetchedAt` (string)
- `finalUrl` (string)
- `links` (array)
- `matches` (array)
- `resource`
- `sourceHash` (string)
- `status` (integer)
- `text` (string)
- `title`
- `truncated` (boolean)
- `url` (string)
- `warnings` (array)
- `x402Version` (number)

### `inspect_openapi` (~62 tokens)

Inspect OpenAPI

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

Input parameters:

- `idempotency_key` (string, required): Stable key used to make a paid retry idempotent.
- `spec` (required): OpenAPI JSON document to inspect; remote references are not fetched.

Output parameters:

- `accepts` (array)
- `error`
- `extensions`
- `openapi` (string)
- `operations` (array)
- `resolvedReferences` (integer)
- `resource`
- `servers` (array)
- `title`
- `version` (string)
- `warnings` (array)
- `x402Version` (number)

### `plan_api_request` (~92 tokens)

Plan API request

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

Input parameters:

- `idempotency_key` (string, required): Stable key used to make a paid retry idempotent.
- `method` (string): Optional HTTP method selector.
- `operation_id` (string): Preferred operationId selector.
- `path` (string): Optional path selector.
- `spec` (required): OpenAPI JSON document containing the operation to plan.

Output parameters:

- `accepts` (array)
- `error`
- `extensions`
- `operation`
- `request`
- `resource`
- `warnings` (array)
- `x402Version` (number)

### `diff_openapi` (~61 tokens)

Diff OpenAPI

Compare two caller-supplied OpenAPI JSON documents.

Input parameters:

- `after` (required): Later OpenAPI JSON document.
- `before` (required): Earlier OpenAPI JSON document.
- `idempotency_key` (string, required): Stable key used to make a paid retry idempotent.

Output parameters:

- `accepts` (array)
- `added` (array)
- `breaking` (boolean)
- `changed` (array)
- `comparedAt` (string)
- `error`
- `extensions`
- `removed` (array)
- `resource`
- `x402Version` (number)

### `get_chain_balance` (~103 tokens)

Read a native Base balance.

Input parameters:

- `address` (string, required): EVM wallet address whose native balance should be read.
- `block`: Optional block number or block tag such as latest.
- `idempotency_key` (string, required): Stable key used to make a paid retry idempotent.
- `network` (string): CAIP-2 network identifier; use eip155:8453 for Base mainnet or eip155:84532 for Base Sepolia.

Output parameters:

- `accepts` (array)
- `address` (string)
- `balanceWei` (string)
- `block` (string)
- `error`
- `extensions`
- `network` (string)
- `observedAt` (string)
- `resource`
- `x402Version` (number)

### `get_chain_transaction` (~90 tokens)

Read a Base transaction and receipt.

Input parameters:

- `idempotency_key` (string, required): Stable key used to make a paid retry idempotent.
- `network` (string): CAIP-2 network identifier; use eip155:8453 for Base mainnet or eip155:84532 for Base Sepolia.
- `tx_hash` (string, required): Transaction hash to inspect on the selected Base network.

Output parameters:

- `accepts` (array)
- `blockNumber`
- `confirmations` (integer)
- `error`
- `extensions`
- `hash` (string)
- `network` (string)
- `observedAt` (string)
- `receipt`
- `resource`
- `status` (string)
- `transaction`
- `x402Version` (number)

### `get_erc20_balance` (~125 tokens)

Read one ERC-20 balance on Base.

Input parameters:

- `address` (string, required): EVM wallet address whose token balance should be read.
- `block`: Optional block number or block tag such as latest.
- `idempotency_key` (string, required): Stable key used to make a paid retry idempotent.
- `network` (string): CAIP-2 network identifier; use eip155:8453 for Base mainnet or eip155:84532 for Base Sepolia.
- `token` (string, required): ERC-20 contract address on the selected Base network.

Output parameters:

- `accepts` (array)
- `address` (string)
- `balanceAtomic` (string)
- `block` (string)
- `decimals` (integer)
- `error`
- `extensions`
- `network` (string)
- `observedAt` (string)
- `resource`
- `symbol` (string)
- `token` (string)
- `x402Version` (number)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/xyz-task402-x402-docs/task402#diagnostics

## Score history

- 2026-10-17: 69
- 2026-10-16: 69
- 2026-10-15: 68
- 2026-10-14: 68
- 2026-10-13: 67
- 2026-10-12: 67
- 2026-10-11: 60

## Common questions

### What is the Task402 Agent Evidence Tools MCP server?

Task402 Agent Evidence Tools is an MCP server listed in the public MCP registry as xyz.task402/x402-docs. Paid evidence tools for PDFs, public webpages, OpenAPI contracts, and Base chain data for AI agents. This page covers its hosted endpoint (https://task402.xyz/mcp).

### Is the Task402 Agent Evidence Tools MCP server safe to use?

Task402 Agent Evidence Tools scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Task402 Agent Evidence Tools MCP server expose?

Task402 Agent Evidence Tools exposes 20 tools: generate_pdf, get_pdf_job, inspect_pdf, get_document_map, search_document, and 15 more. Their descriptions and schemas cost roughly 1,842 tokens of context every time the server is loaded.

### Does the Task402 Agent Evidence Tools MCP server require authentication?

No. We connected to Task402 Agent Evidence Tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Task402 Agent Evidence Tools MCP server still maintained?

Task402 Agent Evidence Tools is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://task402.xyz/mcp
- Repository: https://github.com/xbckz/task402
- Website: https://task402.xyz/
- Changelog RSS feed: https://verifymcp.io/servers/xyz-task402-x402-docs/task402.xml
- Changelog JSON feed: https://verifymcp.io/servers/xyz-task402-x402-docs/task402.json
- HTML version of this page: https://verifymcp.io/servers/xyz-task402-x402-docs/task402