Skip to main content
Glama
richarda23

Edinburgh Festivals MCP Server

by richarda23
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

edfringe-mcp

An MCP server to query the Edinburgh Festivals API for information about events and venues for all the Edinburgh festivals, inluding historical data.

Note that access to Fringe event data for 2025 is only supported on request. Running this MCP remotely would need approval by Edinburgh Fringe.

Tools

  • search_edinburgh_festivals: Search for events based on location, genre, date, or text.

  • search_edinburgh_festival_venues: Search for venues based on festival type, postcode or other criteria.

Some prompts are also available to frame queries with correct context.

Related MCP server: eventin-mcp-server

Example queries

  • what's on at the Gilded Balloon tonight? -> Which of these are comedy?

  • What disabled access is there at the Assembly rooms?

  • When did Gordon Brown last speak at the Book festival?

If you have a Google Maps key added, routing and navigation is supported too or, install a Google Maps MCP)

  • How long does it take to walk between the Gilded Balloon and the Pleasance?

Requirements

  • Python 3.12+

  • uv

Setup

  1. Create an Edinburgh Festival API account.

  2. Clone or download this project.
    Create a .env file in the project root containing:

    api_secret=your_secret
api_key=your_key

    If you have a Google Maps API key you can add

    GOOGLE_MAPS_API_KEY=your API key

    and that will enable timing and route calculations between venues.

  3. Install dependencies:

    uv sync

  4. Add the following MCP configuration to your mcp.json config file in your LLM client app:

    "edinburghFestival": {
    "command": "uv",
    "args": [
        "--directory",
        "/full/path/to/edfringe-mcp",
        "run",
        "main.py"
    ]
}

Development

Running tests:

uv sync --all-groups
uv run pytest

License

This project is licensed under the MIT License. See LICENSE for details.

Available Tools

3 tools
edinburgh_festival_eventsC

Searches this year's Edinburgh festival events. :param datetime_from: An optional ISO8601-like timestamp. e.g. '2025-08-12 00:00:00' :param datetime_to: An optional ISO8601-like timestamp. e.g. '2025-08-12 00:00:00' :param festival: possible values are fringe, demofringe, jazz, book, international, tattoo, art, hogmanay, science, imaginate, film, mela, storytelling. :param genre: The genre of the show. This will vary by festival type but may include comedy, theatre etc :param venue_name: The genre of the show. This will vary by festival type but may include comedy, theatre etc :param search_text: description of the show to search for. :param artist: Name of an artist or performer to search for. :param title: the title of the show to search for. :param year: The year of the festival. Defaults to "*", which means all years. :param datetime_from: The start date and time for the search range. :param number_of_results: The maximum number of results to retrieve, up to 100 at a time. :param page: The page number for pagination, starting from 0. :return:

ParametersJSON Schema
NameRequiredDescriptionDefault
datetime_fromNo2025-01-01 00:00:00
datetime_toNo2025-12-31 23:59:59
festivalNointernational
genreNo
venue_nameNo
search_textNo
titleNo
artistNo
number_of_resultsNo
pageNo
yearNo*

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2.7/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden but provides minimal behavioral information. It mentions pagination and a 100-result limit, but doesn't cover important aspects like authentication requirements, rate limits, error conditions, or what happens with invalid parameters. The return format is hinted at but not explained.

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?

Poorly structured with parameter documentation mixed into the description rather than separate. Contains redundant information (datetime_from appears twice), contradictory statements ('this year's' vs year parameter), and incorrect parameter descriptions. The single opening sentence is followed by a parameter dump without clear organization.

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?

Given 11 parameters with no schema descriptions and no annotations, the description provides substantial parameter information but has significant gaps. The presence of an output schema reduces the need to describe return values, but behavioral aspects like authentication, error handling, and rate limits are missing. The contradictory statements about temporal scope undermine completeness.

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

Parameters4/5

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

With 0% schema description coverage, the description provides substantial parameter documentation, explaining 11 parameters with examples and constraints. However, there are issues: 'venue_name' incorrectly repeats the 'genre' description, and 'datetime_from' appears twice with different explanations. Still, it compensates well for the schema gap.

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

Purpose3/5

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

The description starts with 'Searches this year's Edinburgh festival events' which clearly states the verb (search) and resource (events), but it's vague about scope - 'this year's' contradicts the 'year' parameter allowing all years. It doesn't distinguish from sibling tools like venue-related tools, though the purpose is reasonably clear.

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

Usage Guidelines2/5

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 the sibling venue tools (edinburgh_festival_venue_routes, edinburgh_festival_venues). The description mentions searching 'this year's' events but the year parameter defaults to all years, creating confusion about temporal scope without explicit usage context.

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

edinburgh_festival_venue_routesC

Calculate route between venues

ParametersJSON Schema
NameRequiredDescriptionDefault
originYes
destinationYes

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

C2.7/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool calculates routes but doesn't describe what the output includes (e.g., distance, time, directions), whether it's real-time or cached, any rate limits, or authentication needs. This leaves significant gaps for a routing tool.

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 a single, clear sentence with no wasted words. It's front-loaded and efficiently communicates the core purpose without unnecessary elaboration, making it easy to parse quickly.

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?

Given the tool has an output schema (which should cover return values), the description's job is lighter. However, with no annotations and low schema coverage, it still lacks details on behavioral aspects like route type or constraints. It's minimally adequate but could be more informative for a routing operation.

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?

The schema description coverage is 0%, so the description must compensate. It mentions 'venues' but doesn't clarify what format the origin and destination parameters should be in (e.g., venue names, IDs, addresses) or provide examples. This adds minimal value beyond the schema's basic property names.

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

Purpose3/5

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

The description 'Calculate route between venues' clearly states the action (calculate route) and resource (venues), which is adequate. However, it doesn't specify what type of route (walking, driving, etc.) or distinguish it from potential sibling tools like 'edinburgh_festival_venues' which might provide venue information rather than routing.

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

Usage Guidelines2/5

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. It doesn't mention the sibling tools 'edinburgh_festival_events' or 'edinburgh_festival_venues', nor does it specify prerequisites like needing venue names from another tool first. Usage context is implied but not explicit.

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

edinburgh_festival_venuesC

Search Edinburgh festival venues

ParametersJSON Schema
NameRequiredDescriptionDefault
festivalNointernational
postcodeNo
nameNo
yearNo2025
number_of_resultsNo
pageNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2.4/5.0
Behavior1/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure but offers none. It doesn't indicate whether this is a read-only operation, what permissions might be needed, whether it's paginated (though parameters suggest it might be), rate limits, or what the search returns. The description is purely functional without any behavioral context.

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 extremely concise at just three words, with zero wasted language. It's front-loaded with the core action ('Search') and resource. While it lacks detail, it's structurally efficient and doesn't bury key information.

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

Completeness2/5

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

Given the tool has 6 parameters with 0% schema coverage, no annotations, and an output schema (which helps but doesn't compensate for input gaps), the description is inadequate. It doesn't explain what the search does, how parameters interact, or what results to expect. For a search tool with multiple filtering options, this leaves too much undefined for effective use.

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?

The schema description coverage is 0%, meaning none of the 6 parameters have descriptions in the schema. The tool description doesn't mention any parameters at all, failing to compensate for this gap. Parameters like 'festival', 'postcode', 'name', 'year', 'number_of_results', and 'page' are completely undocumented in both schema and description, leaving their semantics unclear.

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

Purpose3/5

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

The description 'Search Edinburgh festival venues' clearly states the verb ('search') and resource ('Edinburgh festival venues'), making the basic purpose understandable. However, it doesn't distinguish this tool from its sibling 'edinburgh_festival_events' (which presumably searches events rather than venues) or 'edinburgh_festival_venue_routes' (which likely provides routing information). The description is functional but lacks specificity about what makes this search tool unique.

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

Usage Guidelines2/5

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 its siblings. There's no mention of alternatives, exclusions, or specific contexts where this tool is preferred. The agent must infer usage from the tool name alone, which is insufficient for optimal tool selection.

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 updates
    • First observededinburgh_festival_events
    • First observededinburgh_festival_venue_routes
    • First observededinburgh_festival_venues
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3/5.0

Scored across 3 tools

Disambiguation5/5

The three tools have clearly distinct purposes: one searches for events, one searches for venues, and one calculates routes between venues. There is no overlap in functionality, making it easy for an agent to select the right tool for each task.

Naming Consistency5/5

All tool names follow a consistent snake_case pattern with the prefix 'edinburgh_festival_' followed by a descriptive noun phrase (events, venue_routes, venues). This uniformity makes the tool set predictable and easy to understand.

Tool Count3/5

With only three tools, the server feels somewhat thin for a festivals domain that might benefit from additional operations like booking tickets, getting event details, or managing schedules. However, the tools cover core search and navigation needs, keeping it borderline but functional.

Completeness3/5

The tools provide good search capabilities for events and venues, plus route calculation, but there are notable gaps. For example, there is no tool to retrieve detailed information about a specific event or venue, update data, or handle user interactions like favorites or reviews, which limits comprehensive festival management.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers