BOZOS

Read a public HTTPS page or PDF as text with source and citation metadata

readSource

Read-only

Read a public HTTPS page or PDF as text with source and citation metadata. Returns the page text itself, not a model-written summary, so you can quote and cite it. No AI model. Checks robots.txt for BOZOSReader, does not execute scripts, stores no content in the application, and makes outbound public HTTPS requests. Supports HTML, Markdown, plain text, and the text layer of PDFs (pages gives each page's code-point range); no OCR or JavaScript rendering. Limits: 15 seconds, 3 page redirects, 2 MiB source (10 MiB and 300 pages for PDFs), 100000 output code points. GET also accepts url, max_characters and format directly, or a JSON body in ?json= / ?b64=. Declared canonical URL and author/date fields are publisher-supplied and unverified. Cite final_url. Errors always return JSON. gzip, deflate, and Brotli response bodies are decoded before the size limit and source hash are computed. Headless instructions: https://bozos.si/tools/source-reader.md. Source failures include recovery and upstream. For upstream_error, robots_unavailable, and retry_after_redirect, upstream contains stage (robots or source), HTTP status, and parsed Retry-After seconds; other failures set upstream to null. No automatic retries or waiting. Redirects requesting a future delay stop with retry_after_redirect. For retry_later failures with a valid upstream delay, the response exposes a Retry-After header; MCP preserves it in si.bozos/retry-after metadata. Upstream failures continue to use HTTP 424. Set include_quote_source:true with JSON output to also receive the exact matching text from this retrieval, with its own hash and truncation flag. HTML text excludes generated titles and link destinations; Markdown/plain text keep literal syntax (outer whitespace trimmed); PDFs use the text layer. Reuse quote_source.source_text and source_truncated in supplied-text checks. Keep original retrieval metadata yourself. The second representation is opt-in and independently bounded by max_characters. Same as POST https://bozos.si/api/v1/source-reader.

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": "readSource"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	Public HTTPS URL on the default port, without credentials. Private addresses and IP literals are blocked.
`max_characters`	No	Maximum returned Unicode code points per representation. Markdown and optional quote_source text are truncated independently.
`include_quote_source`	No	JSON only. Include quote_source: the literal matching text, its SHA-256, length, PDF page ranges, and independent truncation flag, from this same retrieval. Reuse source_text and source_truncated in Quote Checker or Citation Checker without fetching again. Increases response size; omitted by default.

Output Schema

Name	Required	Description
`pages`	No	PDF only: one entry per page with its one-based number and code-point range [start, end) in markdown. Null for other sources.
`title`	Yes
`output`	Yes
`markdown`	Yes
`final_url`	Yes
`integrity`	Yes
`extraction`	No	main-content, readability, body, passthrough, or pdf-text-layer.
`quote_source`	No	Present only with include_quote_source:true and format=json. Matching text from the same source retrieval, using the same extraction as URL Quote Checker with the same max_characters. Null if Markdown exists but no literal matching text was extracted. Keep final_url, retrieved_at, and integrity with this response; resubmitting text does not verify its provenance.
`retrieved_at`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 25, 2026

addedInput schema / properties / include_quote_source

Added value: +{
+  "default": false,
+  "description": "JSON only. Include quote_source: the literal matching text, its SHA-256, length, PDF page ranges, and independent truncation flag, from this same retrieval. Reuse source_text and source_truncated in Quote Checker or Citation Checker without fetching again. Increases response size; omitted by default.",
+  "type": "boolean"
+}

changedInput schema / properties / max_characters / description

Previous value: -"Maximum returned Unicode code points. Truncation is explicitly marked."New value: +"Maximum returned Unicode code points per representation. Markdown and optional quote_source text are truncated independently."

addedOutput schema / properties / quote_source

Added value: +{
+  "additionalProperties": false,
+  "description": "Present only with include_quote_source:true and format=json. Matching text from the same source retrieval, using the same extraction as URL Quote Checker with the same max_characters. Null if Markdown exists but no literal matching text was extracted. Keep final_url, retrieved_at, and integrity with this response; resubmitting text does not verify its provenance.",
+  "properties": {
+    "characters": {
+      "maximum": 100000,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "checked_text_sha256": {
+      "description": "SHA-256 of source_text encoded as UTF-8, after its own truncation. A content identifier, not a truth or origin guarantee.",
+      "pattern": "^[0-9a-f]{64}$",
+      "type": "string"
+    },
+    "full_characters": {
+      "minimum": 1,
+      "type": "integer"
+    },
+    "pages": {
+      "description": "PDF page numbers and code-point ranges [start, end) in source_text; null for other source types. Supplied-text checks do not automatically retain these page labels.",
+      "items": {
+        "properties": {
+          "end": {
+            "type": "integer"
+          },
+          "page": {
+            "type": "integer"
+          },
+          "start": {
+            "type": "integer"
+          }
+        },
+        "required": [
+          "page",
+          "start",
+          "end"
+        ],
+        "type": "object"
+      },
+      "type": [
+        "array",
+        "null"
+      ]
+    },
+    "representation": {
+      "enum": [
+        "extracted_html_text",
+        "pdf_text_layer",
+        "literal_text"
+      ],
+      "type": "string"
+    },
+    "source_text": {
+      "description": "Exact text to submit as source_text. Offsets and checked_text_sha256 refer to this string unchanged. HTML excludes generated titles, Markdown syntax, metadata, and link destinations. Plain text and Markdown retain their literal syntax with outer whitespace trimmed, as in URL Quote Checker.",
+      "maxLength": 100000,
+      "minLength": 1,
+      "type": "string"
+    },
+    "source_truncated": {
+      "description": "Pass this flag to the supplied-text checker. Independent of output.truncated, which describes Markdown.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "source_text",
+    "source_truncated",
+    "representation",
+    "characters",
+    "full_characters",
+    "checked_text_sha256",
+    "pages"
+  ],
+  "type": [
+    "object",
+    "null"
+  ]
+}

Changed2 schema fields changedOct 25, 2026

addedOutput schema / properties / extraction

Added value: +{
+  "description": "main-content, readability, body, passthrough, or pdf-text-layer.",
+  "type": "string"
+}

addedOutput schema / properties / pages

Added value: +{
+  "description": "PDF only: one entry per page with its one-based number and code-point range [start, end) in markdown. Null for other sources.",
+  "items": {
+    "properties": {
+      "end": {
+        "type": "integer"
+      },
+      "page": {
+        "type": "integer"
+      },
+      "start": {
+        "type": "integer"
+      }
+    },
+    "required": [
+      "page",
+      "start",
+      "end"
+    ],
+    "type": "object"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}

Changed2 schema fields changedOct 24, 2026

removedInput schema / properties / format

Removed value: -{
-  "default": "json",
-  "enum": [
-    "json",
-    "markdown"
-  ],
-  "type": "string"
-}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "final_url": {
+      "format": "uri",
+      "type": "string"
+    },
+    "integrity": {
+      "properties": {
+        "markdown_sha256": {
+          "type": "string"
+        },
+        "source_bytes": {
+          "type": "integer"
+        },
+        "source_sha256": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "markdown": {
+      "type": "string"
+    },
+    "output": {
+      "properties": {
+        "characters": {
+          "type": "integer"
+        },
+        "full_characters": {
+          "type": "integer"
+        },
+        "truncated": {
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "retrieved_at": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "title": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "schema_version",
+    "requested_url",
+    "final_url",
+    "title",
+    "markdown",
+    "retrieved_at",
+    "integrity",
+    "output",
+    "citation",
+    "safety"
+  ],
+  "type": "object"
+}

AddedOct 24, 2026

TDQS

A3.6/5.0

Behavior5/5

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

Annotations already establish read-only, open-world, non-destructive behavior, but the description adds substantial detail: robots.txt checking, no script execution, no content storage, outbound HTTPS, size/time/redirect limits, compression decoding, PDF text-layer limitations, and a detailed error and retry taxonomy. There is no contradiction with the annotations.

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

Conciseness2/5

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

The first sentence is front-loaded and clear, but the description then becomes a dense run-on covering HTTP error stages, Retry-After metadata, 424 responses, and API endpoint equivalences. Much of that belongs in the linked headless instructions or output/error documentation rather than the tool selection description.

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

Completeness5/5

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

Given the output schema, rich annotations, and 100% parameter description coverage, the description is contextually complete. It covers formats, limits, PDF behavior, robots enforcement, quote-source opt-in, and error recovery, so an agent has enough information to invoke it correctly despite the verbosity.

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

Parameters2/5

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

Schema description coverage is 100%, so the schema already documents `url`, `max_characters`, and `include_quote_source`; the description mostly repeats those semantics. It also mentions a `format` parameter accepted by the underlying GET API that is absent from the MCP input schema, which has `additionalProperties: false`, creating a risk of misleading the agent.

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: read a public HTTPS page or PDF as text with source and citation metadata, and clarifies that it returns raw page text rather than a model summary. However, it never distinguishes this from the sibling `fetch` tool, leaving the agent unable to choose between them from the description alone.

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?

Provides useful context that the output can be quoted and cited, and instructs reuse of `quote_source` in Quote Checker or Citation Checker to avoid refetching. But it gives no explicit when-to-use/when-not-to-use guidance against alternatives such as `fetch`, `checkQuote`, or `checkCitations`.

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

All BOZOS tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?