Skip to main content
Glama

ProofFetch — Cited Web Evidence

Get cited page text (uses a key credit)

proof_fetch_evidence

Fetch a public URL and return its cited, paragraph-addressable text with integrity hashes and a receipt. Uses one credit from a ProofFetch key, and only when extraction succeeds. Needs the key sent as the MCP request header Authorization: Bearer : a free key holds 1,000 extractions (no card, POST /v1/keys/free or the ProofFetch home page); a paid key holds 500 for $5.00 (sold on the ProofFetch home page). Example: {"url":"https://example.com/"}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "proof_fetch_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesRequired: the address of one public web page or PDF, for example https://example.com/; a bare domain such as example.com also works. Not a search phrase or placeholder. No credentials, private networks, authenticated pages or browser rendering.
imagesNoWith markdown: keep images as ![alt](src) (true, the default) or leave them out.
extractNoFill a JSON schema from the page's own structured data, no AI: each field is read from a CSS selector you give (selectors or the field's x-selector), else JSON-LD, meta tags or microdata. derived.extract.sources names where each value came from; fields with no source come back null and are listed in missing.
formatsNoOptional extra outputs in derived: markdown (clean Markdown with headings, lists, tables and links; the main content by default), links (every link on the page, absolute, marked internal or not), metadata (title, description, author, dates, Open Graph, JSON-LD). Each is fingerprinted (derived.sha256) and can be recomputed from the page bytes with the open verifier.
maxCharsNoMaximum normalized characters to extract. Free preflight returns metadata plus a preview of about the first 1,000 characters.
idempotencyKeyNoOptional. The same value on a retry within 7 days returns the stored result without using a second credit; a call without one is a new purchase.
removeSelectorNoWith markdown: drop the parts of the page matching this CSS selector before reading, for example ".ads, .comments".
targetSelectorNoWith markdown: read only the parts of the page matching this CSS selector, for example "article" or "#pricing".
onlyMainContentNoWith markdown: leave out menus, headers, footers, cookie notices and sidebars (true, the default) or keep the whole page (false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / extract
      Added value: +{
      +  "description": "Fill a JSON schema from the page's own structured data, no AI: each field is read from a CSS selector you give (selectors or the field's x-selector), else JSON-LD, meta tags or microdata. derived.extract.sources names where each value came from; fields with no source come back null and are listed in missing.",
      +  "examples": [
      +    {
      +      "schema": {
      +        "properties": {
      +          "name": {
      +            "type": "string"
      +          },
      +          "price": {
      +            "type": "number"
      +          }
      +        },
      +        "type": "object"
      +      }
      +    }
      +  ],
      +  "properties": {
      +    "schema": {
      +      "type": "object"
      +    },
      +    "selectors": {
      +      "type": "object"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / formats
      Added value: +{
      +  "description": "Optional extra outputs in derived: markdown (clean Markdown with headings, lists, tables and links; the main content by default), links (every link on the page, absolute, marked internal or not), metadata (title, description, author, dates, Open Graph, JSON-LD). Each is fingerprinted (derived.sha256) and can be recomputed from the page bytes with the open verifier.",
      +  "examples": [
      +    [
      +      "markdown",
      +      "links"
      +    ]
      +  ],
      +  "items": {
      +    "enum": [
      +      "markdown",
      +      "links",
      +      "metadata"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / images
      Added value: +{
      +  "default": true,
      +  "description": "With markdown: keep images as ![alt](src) (true, the default) or leave them out.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / onlyMainContent
      Added value: +{
      +  "default": true,
      +  "description": "With markdown: leave out menus, headers, footers, cookie notices and sidebars (true, the default) or keep the whole page (false).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / removeSelector
      Added value: +{
      +  "description": "With markdown: drop the parts of the page matching this CSS selector before reading, for example \".ads, .comments\".",
      +  "maxLength": 500,
      +  "type": "string"
      +}
    • addedInput schema / properties / targetSelector
      Added value: +{
      +  "description": "With markdown: read only the parts of the page matching this CSS selector, for example \"article\" or \"#pricing\".",
      +  "maxLength": 500,
      +  "type": "string"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / url / description
      Previous value: -"Public HTTP(S) document URL. No credentials, private networks, authenticated pages or browser rendering."New value: +"Required: the address of one public web page or PDF, for example https://example.com/; a bare domain such as example.com also works. Not a search phrase or placeholder. No credentials, private networks, authenticated pages or browser rendering."
    • removedInput schema / properties / url / format
      Removed value: -"uri"
  3. Changed1 schema field changed
    • changedInput schema / properties / idempotencyKey / description
      Previous value: -"Optional. The same value on a retry returns the stored result without using a second credit; a call without one is a new purchase."New value: +"Optional. The same value on a retry within 7 days returns the stored result without using a second credit; a call without one is a new purchase."
  4. Added
  5. Removed
  6. Changed1 schema field changed
    • changedInput schema / properties / idempotencyKey / description
      Previous value: -"Recommended. Send the same key when retrying so a retry never uses a second credit; without it every call is a new purchase."New value: +"Optional. The same value on a retry returns the stored result without using a second credit; a call without one is a new purchase."
  7. Changed1 schema field changed
    • changedInput schema / properties / maxChars / description
      Previous value: -"Maximum normalized characters to extract. Free preflight returns metadata only, never the extracted text."New value: +"Maximum normalized characters to extract. Free preflight returns metadata plus a preview of about the first 1,000 characters."
  8. Added

TDQS

A3.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, so the description is not the only source of the write-ish and open-world character. It still adds real value beyond them: credits are consumed only when extraction succeeds, the key must arrive as an Authorization Bearer header, and results carry integrity hashes and a receipt. It does not mention rate limits or failure/timeout behaviour, which keeps it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core capability is front-loaded in the first sentence, but the bulk of the remainder is commercial detail - free key holds 1,000 extractions, paid key holds 500 for $5.00, sold on the home page - which does little to help an agent invoke the tool correctly. Pricing and acquisition paths crowd out more useful invocation detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With nine parameters, a nested extract object and no output schema, the description does well to sketch the return payload (paragraph-addressable text, derived hashes, receipt) in the absence of an output schema. It is less complete on auth failure modes and on what happens when extraction fails after a key is presented, which matters for a credit-consuming call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and each parameter is documented in the schema itself, so the baseline is 3. The description only restates the single URL example and the key-credit model; it adds no semantics for the nine parameters that the schema does not already carry.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource - fetch a public URL and return its cited, paragraph-addressable text with hashes and a receipt - which an agent can distinguish from a crawl or map operation on scope alone. It does not name the sibling tools (proof_fetch_crawl, proof_fetch_preflight) so the differentiation is implicit rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the context of use clear (a single public page, one key credit, charged only on successful extraction) and the auth requirement is spelled out. However, it never says when to choose this over proof_fetch_crawl or proof_fetch_preflight, leaving the agent to infer that this is the single-page option.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.