Skip to main content
Glama
Sign In
CrawlForge MCP Server

CrawlForge MCP Server

by mysleekdesigns
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

process_document

Read-onlyIdempotent

Use this to extract text from a PDF or DOCX URL or file - research papers, contracts, reports. The body decides how it is read: a PDF or Word document served under sourceType "url" still reaches its parser, and a body this tool cannot read…

Instructions

Use this to extract text from a PDF or DOCX URL or file - research papers, contracts, reports. The body decides how it is read: a PDF or Word document served under sourceType "url" still reaches its parser, and a body this tool cannot read (an image, an archive) is refused by name. Returns structured sections, metadata, and word count; for a PDF, pagesRead names the pages read (maxPages defaults to 100). Not for ordinary web pages (scrape), though an HTML URL is accepted. A local file (sourceType file/pdf_file) must be .pdf, .docx, .txt, .md or .html and outside dot-directories; CRAWLFORGE_ALLOWED_DIRS limits reads to the listed directories. Cost: 2 credits. Example: process_document({source: "https://example.com/report.pdf", sourceType: "pdf_url"})

Input Schema

NameRequiredDescriptionDefault
sourceYesDocument source - URL or file path
optionsNoAdditional processing options (maxPages, pageRange:{start,end}, extractText, extractMetadata, outputFormat, ...)
redact_piiNoRedact personal data from the text this call returns, before it reaches your context window. true means the free regex pass over EMAIL, PHONE, FINANCIAL and SECRET. The result carries redaction:{entities,count}. Default: off
sourceTypeNoType of document source
user_agentNoOverride the outbound User-Agent. CrawlForge identifies itself honestly by default; use this only for targets you have your own agreement with.
respect_robotsNoRespect the target site's robots.txt (default: true). Setting this to false is honoured, returns a warning in the response, and is recorded against your API key — it is your decision, not a silent default.
max_inline_charsNoLargest result to return inline, in characters of its JSON. Over it, the call returns a preview plus a result_handle for read_result instead of the whole result (default 40,000; env CRAWLFORGE_MAX_INLINE_CHARS)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv6.0.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / max_inline_chars
      Added value: +{
+  "description": "Largest result to return inline, in characters of its JSON. Over it, the call returns a preview plus a result_handle for read_result instead of the whole result (default 40,000; env CRAWLFORGE_MAX_INLINE_CHARS)",
+  "maximum": 10000000,
+  "minimum": 1000,
+  "type": "integer"
+}
    • changedInput schema / properties / options / additionalProperties
      Previous value: -trueNew value: +{}
    • addedInput schema / properties / redact_pii
      Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "properties": {
+        "entities": {
+          "description": "Which classes to redact, case-insensitive: EMAIL, PHONE, FINANCIAL, SECRET, plus PERSON and LOCATION when mode is \"model\". Omitted or empty means all four regex classes (and both model classes in \"model\" mode). An unknown name, or a model-only name without mode:\"model\", is rejected",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "mode": {
+          "description": "\"fast\" (default) is regex only and free; \"model\" adds an Ollama NER pass for PERSON and LOCATION (+3 credits once per call)",
+          "enum": [
+            "fast",
+            "model"
+          ],
+          "type": "string"
+        },
+        "replace_style": {
+          "description": "\"tag\" (default) writes <EMAIL>, \"mask\" writes [REDACTED], \"remove\" deletes the value",
+          "enum": [
+            "tag",
+            "mask",
+            "remove"
+          ],
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  ],
+  "description": "Redact personal data from the text this call returns, before it reaches your context window. true means the free regex pass over EMAIL, PHONE, FINANCIAL and SECRET. The result carries redaction:{entities,count}. Default: off"
+}
  2. Changed2 schema fields changedv5.4.0
    • addedInput schema / properties / respect_robots
      Added value: +{
+  "description": "Respect the target site's robots.txt (default: true). Setting this to false is honoured, returns a warning in the response, and is recorded against your API key — it is your decision, not a silent default.",
+  "type": "boolean"
+}
    • addedInput schema / properties / user_agent
      Added value: +{
+  "description": "Override the outbound User-Agent. CrawlForge identifies itself honestly by default; use this only for targets you have your own agreement with.",
+  "type": "string"
+}
  3. Changed2 schema fields changedv5.0.4
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • changedInput schema / properties / options / description
      Previous value: -"Additional processing options (maxPages, pageRange:{start,end}, extractText, extractMetadata, password, outputFormat, ...)"New value: +"Additional processing options (maxPages, pageRange:{start,end}, extractText, extractMetadata, outputFormat, ...)"
  4. First observedv4.10.0

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so safety is covered; the description adds real value with cost (2 credits), the refusal behavior for unreadable bodies, and the pagesRead/maxPages=100 detail. However it never mentions the truncation path — that a large result comes back as a preview plus result_handle for read_result — which is the most consequential behavior for downstream flow, so it falls short of 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 purpose is front-loaded in the first clause, but the rest is one dense paragraph of semicolon-chained caveats and parentheticals that is harder to scan than it needs to be. Nearly every clause carries information, so little is wasted, yet the lack of breakdown costs readability.

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

Completeness4/5

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

For a 7-parameter tool with nested objects and no output schema, the description does well: it states the return shape (structured sections, metadata, word count, pagesRead) and the main refusal and directory constraints. The gap is the large-result/handle handoff and the redaction result field, both of which affect what the agent must do next.

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 coverage is 100%, so the schema already documents all seven parameters including the redact_pii sub-object and max_inline_chars. The description adds genuine meaning for sourceType ('a PDF or Word document served under sourceType "url" still reaches its parser') and maxPages defaulting to 100, which is above baseline, but it says nothing about redact_pii, user_agent, or respect_robots and omits the options object entirely.

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

Purpose5/5

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

Opens with a specific verb+resource ('extract text from a PDF or DOCX') and scopes it to concrete document classes (research papers, contracts, reports). It explicitly distinguishes itself from the nearest sibling by saying it is 'Not for ordinary web pages (scrape)', so an agent can route without opening either schema.

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

Usage Guidelines5/5

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

Gives an explicit when-not and the alternative ('Not for ordinary web pages (scrape), though an HTML URL is accepted'), plus the accepted file extensions and the dot-directory/CRAWLFORGE_ALLOWED_DIRS constraint. The inline example anchors the call shape for the common URL case.

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

Deploy Server

Other Tools