Skip to main content
Glama
koprjaa

theses-mcp

by koprjaa
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Remote

theses-mcp

Search Czech university theses and retrieve document links for MCP clients.

CI MIT license

What it does

  • Searches thesis metadata and full texts on theses.cz.

  • Reads titles, abstracts, keywords, and defense information.

  • Finds thesis files, attachments, and reviewer reports on theses.cz or school repositories.

  • Supports your own authenticated sessions through login, use_cookie, and whoami.

Related MCP server: Primo MCP Server

Install

Install a current stable Rust toolchain, then:

cargo install --git https://github.com/koprjaa/theses-mcp

This puts theses-mcp in ~/.cargo/bin. Add this entry to your MCP client's mcpServers configuration:

{
  "theses": {
    "command": "theses-mcp"
  }
}

No environment variables are required for public access.

Use

Ask your MCP client to call these tools:

search(query="midjourney AND autorství", limit=10)
detail(id_or_url="pl09jx")
fulltext(id_or_url="7lfo74")

Use a record's code or URL for detail and fulltext. Search accepts AND, OR, and quoted phrases. Your client exposes the remaining tool parameters.

fulltext returns file links, not extracted text. Check its files and note fields for availability. Some repositories require login or show a CAPTCHA. Call login with the repository host to sign in using your own account. Sessions persist in ~/.theses-mcp/cookies.json; delete that file to forget them. The file format is the one the earlier Python version wrote, so saved sessions keep working.

Browser login

login opens a window of a Chromium-family browser (Chrome, Edge, Brave, Vivaldi, Opera, or Chromium) with a profile of its own in ~/.theses-mcp/browser, and reads back only the cookies of the host you sign in to. It talks to the browser over the Chrome DevTools Protocol, so nothing is downloaded.

  • On Windows it opens your default browser if that is a Chromium build. On macOS and Linux there is no cheap way to ask, so it uses the first Chromium-family browser it finds at the usual places.

  • Firefox and Safari cannot be driven. Use use_cookie with a cookie copied from the browser's developer tools instead.

  • attach=true uses a browser that is already running with --remote-debugging-port.

Check

theses-mcp --selftest runs the parsers against the live sites. It makes several dozen requests, so run it by hand now and then, not in CI.

License

MIT

Available Tools

3 tools
detailA

Fetch the full record of a thesis from theses.cz.

id_or_url: thesis code ("pl09jx"), /id/pl09jx/ or a full URL. Returns author, title (incl. translation), CS/EN abstracts, keywords, supervisor/opponent, full-text availability and the school archive link.

ParametersJSON Schema
NameRequiredDescriptionDefault
id_or_urlYes

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does clarify that the tool returns specific metadata fields and accepts varying input forms, but it omits any mention of side effects (e.g., read-only nature), error behavior for invalid IDs, or potential access limitations.

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

Conciseness5/5

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

The description is two concise sentences. The first sentence states the tool's core purpose, and the second packs the input format and the return fields into a compact, readable block. No filler or redundant content.

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 simple one-parameter fetch tool, this description is largely complete: it specifies accepted inputs and enumerates the returned record components. However, it lacks explicit statement of not-found/error behavior and does not place itself relative to the sibling search/fulltext tools, making it slightly less than fully complete.

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

Parameters5/5

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

The input schema only defines 'id_or_url' as a string with zero description coverage. The description fully compensates by explaining exactly what this parameter accepts: a thesis code, a path like '/id/pl09jx/', or a full URL. This is complete, actionable semantic information.

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?

The description starts with a specific verb 'Fetch' and names the resource ('the full record of a thesis from theses.cz'). It also enumerates the returned fields, making the tool's purpose unambiguous and sufficiently distinct from the sibling tools 'search' and 'fulltext'.

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 implies that the tool should be used when you already know the thesis identifier or URL, and it even shows accepted formats. However, it never explicitly contrasts this tool with 'search' or 'fulltext', nor does it state when not to use it.

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

fulltextA

Resolve a thesis to downloadable full-text files in its school's repository.

theses.cz stores only metadata; the files live in each school's own system (mostly the IS family — is.muni.cz, is.slu.cz, vskp.vse.cz …). This follows the record to that repository and lists the documents it exposes publicly.

id_or_url: thesis code ("7lfo74"), /id/7lfo74/ or a full URL.

access is the visibility of the theses.cz copy and does NOT decide what you can download: a thesis marked "autentizovaným zaměstnancům ze stejné školy" on theses.cz is often served freely by the school's own repository, so always check files.

Each file carries label, filename and url; extensionless URLs also get confirmed and content_type from a HEAD request. An empty files plus a note means the school really does gate it (login or CAPTCHA) — a real answer, not an error.

ParametersJSON Schema
NameRequiredDescriptionDefault
id_or_urlYes

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does an excellent job. It discloses that the tool follows the record to an external repository, lists publicly exposed documents, notes that the theses.cz `access` field does not determine downloadability, and explains how to interpret file fields and empty results. This gives the agent a realistic model of what happens and what to expect.

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

Conciseness5/5

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

The description is relatively long but every sentence adds essential context: purpose, repository layout, parameter format, access interpretation, file structure, and edge-case handling. It is front-loaded with the main verb and resource, then elaborates in a logical order. No fluff or redundancy.

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 tool's complexity, lack of annotations, and lack of an output schema, the description is exceptionally complete. It explains the output shape (`label`, `filename`, `url`, optional `confirmed` and `content_type`), behavioral nuances (`access` is not determinative), and how to handle empty results (`note` means gated, not an error). The agent has everything needed to invoke and interpret the tool correctly.

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

Parameters5/5

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

There is only one parameter, `id_or_url`, and the schema provides no description for it (0% coverage). The description fully compensates by specifying the accepted formats: 'thesis code ("7lfo74"), /id/7lfo74/ or a full URL.' This is explicit and leaves no ambiguity about what value to pass.

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?

The description opens with a specific verb and resource: 'Resolve a thesis to downloadable full-text files in its school's repository.' This clearly differentiates the tool from siblings `search` and `detail` by focusing on file retrieval rather than discovery or metadata. It also explains why this tool is needed (theses.cz stores only metadata) which further cements its unique purpose.

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

Usage Guidelines4/5

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

The description explains the context of use and provides actionable guidance, such as 'always check `files`' and what an empty `files` plus a `note` means. It does not explicitly name alternatives or say when not to use this tool, but the purpose is clear enough to infer that it is for fulltext resolution, while siblings handle search and detail. Overall, clear context but no explicit exclusions.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv0.1.0
    • First observeddetail
    • First observedfulltext
    • First observedsearch
Deploy Server
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

TDQS

A4.5/5.0

Scored across 3 tools

Disambiguation5/5

Each tool targets a distinct stage of working with theses.cz: search finds theses or fulltext snippets, detail retrieves full metadata for a single record, and fulltext resolves a thesis to downloadable files in its school repository. Even though search and fulltext both deal with PDFs, their purposes are clearly separate.

Naming Consistency5/5

All three tool names are single lowercase words (search, detail, fulltext), following a consistent, minimalist naming convention. While not verb_noun, the style is uniform and predictable, making the set easy to navigate.

Tool Count5/5

With only three tools, the server is tightly scoped for its purpose: searching, inspecting, and retrieving full text from a national thesis registry. Each tool earns its place, and the count fits well within the typical 3-15 range for a focused domain.

Completeness5/5

The toolset covers the complete user journey for the domain: discover via search, examine metadata via detail, and access actual files via fulltext. There are no obvious gaps—it's a read-only service, and lifecycle operations like create/update are not applicable.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • cds-mcp

    MohamedElashri
    A
    license
    A
    quality
    D
    maintenance
    MCP server for searching and retrieving documents, metadata, and files from CERN Document Server (CDS) with optional CERN SSO authentication.
    6
    MIT

  • Primo MCP Server

    geheharidas
    A
    license
    A
    quality
    D
    maintenance
    MCP server for searching Ex Libris Primo library catalogues and subscribed databases, enabling search, record retrieval, autocomplete, citation generation, and export to BibTeX, RIS, or CSV.
    5
    8
    MIT

  • MEK MCP

    wlagyorgy
    F
    license
    A
    quality
    D
    maintenance
    MCP server to access the Hungarian Electronic Library (MEK) search engines, enabling agentic tools to search and retrieve content.
    4
    -