A comprehensive Model Context Protocol (MCP) server for PDF reading, navigation, and text search with cross-platform PDF viewer integration. Built on PyMuPDF (MuPDF), exposed through MCP so the dependency stays isolated from your project environment.
Claude Code's built-in Read tool can open PDFs directly, so it's fair to ask whether this server is still needed. It is — but for a narrower reason than it used to be. The built-in reader has two limitations that this server is designed around, and a third tool (poppler's pdftotext) doesn't fill the gap either:
The built-in Read tool renders each PDF page as a raster image. Two consequences for scientific papers:
It's token-expensive and doesn't scale. A figure-heavy 25-page paper is ~25 page-images; reading it whole burns tens of thousands of image tokens and crowds out the rest of the conversation. You can cap it with a pages range (and recent versions require one past ~10 pages), but only if you already know which pages you want.
Image text isn't searchable. You can't search across pixels. To find where a paper discusses, say, "survivorship bias," you'd read pages as images until you spot it — the exact behavior that fills up context.
Poppler's pdftotext is cheap and searchable but mangles the content scientific papers are made of:
Inline math breaks. Combining marks detach from their base — e.g. p̃(x;t) comes out as a stray ~ on its own line, split from p(x;t).
Multi-column layout scrambles. Default mode drags in running headers and can reorder text; -layout glues the two columns horizontally so every line reads left-column … right-column, destroying reading order and breaking any phrase search that spans a column.
This server uses MuPDF's get_text(), which preserves reading order across columns and keeps inline math intact, and exposes it as cheap, searchable text plus structure/outline navigation. The intended division of labor:
Need | Tool |
Read text, search to the relevant pages, navigate structure | This server (MuPDF text + search) — cheap, searchable, correct reading order |
See a figure, panel, rendered equation, or table | Built-in |
Related MCP server: PDF MCP Server
PDF text extraction - Read full PDFs or specific pages/ranges
PDF structure analysis - Extract table of contents and page summaries
Text search with location - Find text and jump to results
Direct PDF navigation - Open PDFs to specific pages
Cross-platform PDF viewers - Supports Skim, Zathura, Evince, and more
MCP integration - Works with Claude Code and other MCP clients
No dependency issues - PyMuPDF isolated in MCP server environment
# Install with pipx (recommended)
pipx install git+https://github.com/matsengrp/pdf-navigator-mcp.git
# Or install in current environment
pip install git+https://github.com/matsengrp/pdf-navigator-mcp.gitAdd to your ~/.claude.json:
{
"mcpServers": {
"pdf-navigator": {
"type": "stdio",
"command": "pdf-navigator-mcp"
}
}
}In Claude Code, you can:
"Read the abstract from paper.pdf" → Extracts and shows text content
"What's the table of contents for paper.pdf?" → Shows PDF structure
"Read pages 5-10 of paper.pdf" → Extracts specific page range
"Search for 'parameter efficiency' in paper.pdf" → Finds text and locations
"Open paper.pdf to page 5" → Opens PDF viewer to specific page
read_pdf_text(file_path, start_page, end_page) - Extract text from page range
read_pdf_page(file_path, page_number) - Extract text from single page
get_pdf_structure(file_path) - Get table of contents and page summaries
get_pdf_info(file_path) - Get document metadata
search_pdf_text(file_path, query) - Search text and return locations
open_pdf_page(file_path, page_number) - Open PDF viewer to specific page
search_and_open(file_path, query, result_index) - Search and open to result
Skim (macOS) - skim:// URL scheme
Zathura (Linux) - --page argument
Evince (Linux) - --page-index argument
SumatraPDF (Windows) - -page argument
Adobe Acrobat (Cross-platform) - /A page=N argument
Configure your PDF reader in ~/.pdf-navigator-config.json:
{
"pdf_reader": "skim",
"reader_path": "/Applications/Skim.app"
}git clone https://github.com/matsengrp/pdf-navigator-mcp.git
cd pdf-navigator-mcp
pip install -e ".[dev]"MIT License
Get metadata and basic information about a PDF file.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the PDF file |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fails to disclose behavioral traits such as whether the tool requires a local file, performs network access, or has latency. The description only restates the purpose, offering no insight into side effects or requirements beyond the input schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no extraneous words. It is front-loaded with the essential action and resource, making it efficient for an agent to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having an output schema (not shown), the description does not explain what metadata or basic information is returned. For a tool that returns data, this is a significant gap; the agent cannot predict the structure or fields. Additionally, the parameter description could be enhanced with examples or constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for the single parameter file_path, which already states 'Path to the PDF file.' The description adds no additional semantics or constraints (e.g., supported file extensions, absolute vs relative paths). Baseline score of 3 is appropriate given schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (get) and resource (metadata and basic information about a PDF file). It distinguishes from sibling tools like get_pdf_structure and read_pdf_text, which handle structural or textual content. However, it could be more specific about what metadata is included (e.g., page count, file size, author).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus its siblings. There are no explicit statements about prerequisites, such as file availability or format support, nor any comparison to alternatives like search_pdf_text. The usage context is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get PDF structure including table of contents and page summaries.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the PDF file |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description provides minimal behavioral info—no mention of read-only nature, performance, or permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single concise sentence that effectively communicates the tool's purpose without waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With output schema present and only one parameter, the description is mostly complete; could briefly mention that it works on PDF files only.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents the parameter; description adds no extra meaning beyond 'Path to the PDF file'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves PDF structure (TOC and page summaries), distinguishing it from siblings like get_pdf_info or read_pdf_text.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use or not use this tool; it doesn't mention alternatives or context such as preconditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Open a PDF file to a specific page.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the PDF file | |
| page_number | Yes | Page number to open (1-indexed) |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must bear full weight. It does not disclose what 'open' entails (e.g., renders the PDF, returns a view, or modifies state), nor behavior for invalid pages or encrypted files.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description omits what the tool returns (output schema exists but not described) and lacks behavioral context, making it incomplete for reliable use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers both parameters with clear descriptions (path and 1-indexed page number). The description adds little beyond this.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('open'), the resource ('PDF file'), and the destination ('to a specific page'), which distinguishes it from siblings like read_pdf_page or get_pdf_info.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus siblings (e.g., read_pdf_page), nor any prerequisites or when-not-to-use scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read text content from a specific PDF page.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the PDF file | |
| page_number | Yes | Page number to read (1-indexed) |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only states 'Read text content'. It fails to disclose important behaviors like handling of non-text content, page range errors, format of file path, or whether it's safe (read-only). This is insufficient for an agent to understand side effects or requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no unnecessary words, earning its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema (not shown) and multiple siblings, the description is incomplete. It does not explain what the output looks like or when this tool is preferable to others like 'get_pdf_info' or 'search_pdf_text'. The agent lacks sufficient context for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the schema's parameter descriptions. It does not clarify file path format or acceptable page number types beyond what is in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Read', the resource 'text content from a specific PDF page', and distinguishes itself from siblings like 'read_pdf_text' which may read all text and 'open_pdf_page' which may open visually.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'read_pdf_text' or 'search_pdf_text'. The lack of explicit usage context or exclusions makes it difficult for an agent to choose correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read text content from PDF pages.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the PDF file | |
| start_page | No | Starting page number (1-indexed, default: 1) | |
| end_page | No | Ending page number (1-indexed, inclusive). If None, reads to end. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility for behavioral disclosure. It only states 'Read text content' without mentioning limitations (e.g., handling of images, tables, or encrypted files), performance considerations, or side effects. The tool is likely safe, but the description fails to communicate that.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that directly states the tool's purpose. It is front-loaded and efficient, though it could be slightly expanded with no substantial increase in length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema (not detailed but noted as existing), the description does not need to cover return values. However, it lacks context about file access requirements, expected file formats, and error handling. For a simple tool, this is adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, so the schema already documents parameters and their defaults. The description adds no additional semantic meaning beyond what the schema provides, resulting in a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Read text content from PDF pages' clearly states the verb and resource, indicating that it extracts text from PDF pages. However, it does not explicitly distinguish from sibling tools like 'read_pdf_page' or 'search_pdf_text', which could also involve reading text.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. For example, it does not specify that it is for extracting plain text from a range of pages, while 'get_pdf_structure' analyzes layout or 'search_pdf_text' searches for strings. The agent has no context for decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for text in PDF and open to the specified result.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the PDF file | |
| query | Yes | Text to search for | |
| result_index | No | Which search result to open (1-indexed, default: 1) |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states it 'opens' but does not define what that means—whether it opens a viewer, returns content, or affects state. Side effects, permissions, or return behavior are not disclosed, leaving significant ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence of 12 words conveys the core purpose efficiently. It is front-loaded with the verb 'Search' and the resource 'PDF', making the tool's function immediately clear with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having a complete schema and an output schema, the description lacks crucial behavioral context about the 'open' action. It does not explain if the tool returns search result metadata, opens an external viewer, or navigates within a document. This gap makes it incomplete for reliable agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with descriptions for all three parameters. The description adds no new meaning beyond what the schema already explains (e.g., result_index is 1-indexed). Baseline 3 is appropriate as the description does not enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action: 'Search for text in PDF and open to the specified result.' It specifies the resource (PDF) and the operation (search and open), distinguishing it from siblings like search_pdf_text (which likely only returns results without opening) and open_pdf_page (which opens by page number).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied: use when you want to both search and navigate to a result. However, no explicit when-to-use or when-not-to-use guidance is given, nor are alternatives like search_pdf_text mentioned. The agent must infer context from the description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for text in a PDF file and return results with page numbers.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the PDF file | |
| query | Yes | Text to search for |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the full burden. It only states that results include page numbers, but does not disclose search behavior (case sensitivity, substring, pattern matching), performance, or any side effects. The output schema exists but is not described, leaving agents uninformed about the return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence (12 words) with no wasted words. It is appropriately sized for its purpose, though it could benefit from slight structural improvements like bullet points if more details were added.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 2 simple parameters and an output schema (not shown in description), the description fails to provide enough context for effective agent use. It does not specify search options (case sensitivity, whole word), output format (list of matches, positions), or any limitations (e.g., large files). The agent may misinterpret the capabilities.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (both parameters are described in the schema). The description adds no additional meaning beyond the schema. Baseline score of 3 is appropriate; the description does not compensate for any missing semantic context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Search for text in a PDF file and return results with page numbers.' It specifies the verb (search), resource (PDF file), and output (results with page numbers). This distinguishes it from siblings like get_pdf_info (file info) or read_pdf_text (extract all text).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidelines on when to use this tool vs alternatives. For example, if the agent needs to extract all text from a PDF, read_pdf_text would be more appropriate, but this is not mentioned. The description lacks any when-to-use or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_pdf_infoget_pdf_structureopen_pdf_pageread_pdf_pageread_pdf_textsearch_and_opensearch_pdf_textScored across 7 tools
Each tool targets a distinct action: metadata, structure, opening, reading specific page, reading general text, searching with open, and searching. No overlapping purposes.
All tools follow a consistent verb_noun pattern in snake_case, e.g., get_pdf_info, read_pdf_page, search_pdf_text.
7 tools is well-scoped for a PDF navigator, covering information retrieval, structure, reading, and searching without being excessive.
The set covers the full navigation workflow: accessing metadata/structure, opening to a page, reading text, and searching. No obvious gaps for its stated purpose.
Query your own PDFs and documents from any MCP client. Every answer cites the page it came from.
MCP server for the PDFGate API. Generate PDFs, manage documents and handle e-signatures.
Privacy-first PDF tools over MCP: merge, split, rotate, delete, compress, protect, inspect.
Document processing over MCP: merge, split and compress PDFs, run OCR, extract document text.
