Skip to main content
Glama
lmorchard

Oblique Strategies MCP Server

by lmorchard
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Remote

Oblique Strategies MCP Server

An MCP (Model Context Protocol) server that provides access to Brian Eno and Peter Schmidt's Oblique Strategies - a collection of prompts designed to help overcome creative blocks through lateral thinking.

Why?

Why not?

Related MCP server: LLV Helix Framework

No, seriously, why?

Because I've built Oblique Strategies thingies for various devices & platforms and I wanted to make another one to play with the MCP protocol.

This is a very silly project and you should just go buy a real deck of cards.

Quick Start

No installation required, if you have uvx and you trust my code from github. (Weirdo.)

Run directly from GitHub using uvx:

uvx --from git+https://github.com/lmorchard/oblique-strategies-mcp oblique-strategies-mcp

For Claude Desktop, add to your config file:

{
  "mcpServers": {
    "oblique-strategies": {
      "command": "/path/to/uvx",
      "args": [
        "--from",
        "git+https://github.com/lmorchard/oblique-strategies-mcp",
        "oblique-strategies-mcp"
      ]
    }
  }
}

For Claude Code:

claude mcp add oblique-strategies -- /path/to/uvx --from git+https://github.com/lmorchard/oblique-strategies-mcp oblique-strategies-mcp

Features

  • Get random strategies from multiple editions (1975-1982)

  • Search strategies by keyword

  • Choose from 7 different collections including programming-specific adaptations

  • Default: Edition 2 (1978) with 128 strategies

MCP Tools

  • get_strategy - Get a random strategy (optionally specify edition)

  • search_strategies - Search strategies by keyword

  • list_editions - List all available editions

Available Collections

  • Edition 1-4: Original Oblique Strategies (1975-1982)

  • Condensed: Comprehensive collection (195 strategies)

  • Programmers: Programming-specific adaptations (96 prompts)

  • Do It: Action-oriented prompts (32 strategies)

Installation

For Development

# Clone the repository
git clone <repository-url>
cd oblique-strategies-mcp

# Install dependencies with uv
uv sync

Running the Server

Development Mode

From the project directory:

# Using the package entry point
uv run oblique-strategies-mcp

# Or using Python module syntax
uv run python -m oblique_strategies_mcp

# Or using the wrapper script
./run-server.sh

After Global Installation

oblique-strategies-mcp

Configuration

For Claude Desktop

Add to your Claude Desktop config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

Development Setup

{
  "mcpServers": {
    "oblique-strategies": {
      "command": "/path/to/uv",
      "args": [
        "--directory",
        "/path/to/oblique-strategies-mcp",
        "run",
        "oblique-strategies-mcp"
      ]
    }
  }
}

Note: Replace /path/to/uv with the full path to your uv executable (typically ~/.local/bin/uv or use which uv to find it).

Global Installation Setup

{
  "mcpServers": {
    "oblique-strategies": {
      "command": "oblique-strategies-mcp",
      "args": [],
      "env": {}
    }
  }
}

For Claude Code

Development Setup

claude mcp add oblique-strategies -- uv --directory /path/to/oblique-strategies-mcp run oblique-strategies-mcp

Using Wrapper Script

claude mcp add oblique-strategies /path/to/oblique-strategies-mcp/run-server.sh

Global Installation

claude mcp add oblique-strategies oblique-strategies-mcp

After adding, restart Claude Desktop or reconnect in Claude Code.

License

MIT

Acknowledgments

Available Tools

3 tools
get_strategyA

Get a random oblique strategy from the specified edition.

Args: edition: The edition to use (edition-1, edition-2, edition-3, edition-4, condensed, programmers, do-it). Defaults to edition-2.

Returns: A dictionary containing the strategy text and edition information.

ParametersJSON Schema
NameRequiredDescriptionDefault
editionNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4/5.0
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 mentions the tool returns a random strategy, which is useful, but doesn't describe other behavioral traits such as whether it's idempotent, has rate limits, requires authentication, or what happens on errors. For a tool with zero annotation coverage, this leaves significant gaps.

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 appropriately sized and front-loaded, with the core purpose in the first sentence and parameter details in a structured format. Every sentence earns its place by providing essential information without redundancy or fluff.

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?

Given the tool's low complexity (1 parameter) and the presence of an output schema (which handles return values), the description is mostly complete. It covers purpose, parameter details, and return format at a high level. However, it could be more complete by addressing behavioral aspects like randomness or error handling, given the lack of annotations.

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?

The schema description coverage is 0%, so the description must compensate. It provides the parameter 'edition' with a clear list of allowed values (edition-1 through edition-4, condensed, programmers, do-it) and specifies the default as edition-2, adding meaningful semantics beyond the bare schema. This adequately covers the single parameter.

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 clearly states the specific action ('Get a random oblique strategy') and resource ('from the specified edition'), distinguishing it from sibling tools like list_editions and search_strategies. It precisely defines what the tool does without being vague or tautological.

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 provides clear context for when to use this tool (to get a random strategy from a specific edition), but it doesn't explicitly state when not to use it or mention alternatives like search_strategies for non-random searches. The context is clear but lacks explicit exclusions or comparisons.

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

list_editionsB

List all available editions and their descriptions.

Returns: Information about all available editions.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states what the tool does and the return type, missing critical details like whether it's read-only, requires authentication, has rate limits, or pagination behavior. For a tool with no annotations, this is insufficient.

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

Conciseness4/5

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

The description is concise and front-loaded, with the main purpose stated first and a brief note on returns. It avoids unnecessary elaboration, though the 'Returns:' section could be slightly more informative. Overall, it's efficient with minimal waste.

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's simplicity (0 parameters, output schema exists), the description is adequate but lacks depth. It covers the basic purpose and return type, but without annotations, it misses behavioral context. The output schema helps, but the description could better explain what 'Information about all available editions' entails, such as format or scope.

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?

The tool has 0 parameters, and schema description coverage is 100%, so there's no need for parameter details in the description. The description correctly avoids unnecessary parameter information, earning a high score for not adding redundant content beyond the structured schema.

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?

The description clearly states the tool's purpose: 'List all available editions and their descriptions.' It specifies the verb ('List') and resource ('editions'), making the action explicit. However, it doesn't differentiate from sibling tools like 'get_strategy' or 'search_strategies', which prevents a score of 5.

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 sibling tools or contexts where this tool is preferred, such as for browsing all editions versus searching or retrieving specific ones. This lack of comparative usage information limits its helpfulness.

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

search_strategiesB

Search for strategies containing the specified keywords.

Args: query: Keywords to search for (case-insensitive). edition: Optional edition to limit search to. If not specified, searches all editions.

Returns: A dictionary containing matching strategies and their editions.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
editionNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.4/5.0
Behavior2/5

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 mentions that the search is 'case-insensitive', which is useful behavioral context. However, it doesn't disclose other important traits like whether this is a read-only operation, potential rate limits, authentication needs, or pagination behavior for a search tool.

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

Conciseness4/5

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

The description is appropriately sized and front-loaded with the core purpose in the first sentence. The 'Args' and 'Returns' sections are structured clearly, though the 'Returns' section could be slightly more detailed. Overall, it's efficient with minimal waste.

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?

Given the tool's moderate complexity (2 parameters, search functionality), the description is fairly complete. It explains parameters and return values, and an output schema exists, so detailed return explanations aren't needed. However, without annotations, it could benefit from more behavioral context like safety or performance notes.

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?

The description adds significant meaning beyond the input schema, which has 0% description coverage. The 'Args' section explains that 'query' is for 'keywords to search for (case-insensitive)' and 'edition' is 'optional' to 'limit search to', clarifying semantics that aren't in the schema. With 2 parameters and good coverage in the description, this compensates well.

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?

The description clearly states the tool's purpose: 'Search for strategies containing the specified keywords.' It specifies the verb ('search') and resource ('strategies'), but doesn't explicitly differentiate from sibling tools like 'get_strategy' or 'list_editions', which would require a 5.

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 usage through the 'Args' section, which explains when to use the optional 'edition' parameter, but it doesn't provide explicit guidance on when to choose this tool over alternatives like 'get_strategy' or 'list_editions'. No exclusions or prerequisites are mentioned.

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. Dates show when Glama detected each change.

  1. 3 tool updatesv0.1.0
    • First observedget_strategy
    • First observedlist_editions
    • First observedsearch_strategies
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: get_strategy retrieves a random strategy, list_editions provides metadata about available editions, and search_strategies finds strategies by keywords. There is no overlap in functionality, and an agent can easily distinguish between them.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (get_strategy, list_editions, search_strategies) with clear, descriptive verbs. The naming is uniform and predictable throughout the set.

Tool Count5/5

With 3 tools, this server is well-scoped for its purpose of accessing Oblique Strategies. Each tool earns its place by covering essential operations: retrieving random strategies, listing editions, and searching. This count is appropriate and avoids bloat.

Completeness5/5

The tool surface is complete for the domain of accessing and querying Oblique Strategies. It covers random retrieval, metadata listing, and keyword search across editions, with no obvious gaps. Agents can perform all core workflows without dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • LLV Helix Framework

    suhitanantula
    A
    license
    B
    quality
    C
    maintenance
    Implements the Lines-Loops-Vibes creativity operating system with tools for building strategic flows, creating iterative loops, and managing energy states. Provides pre-built templates for innovation, strategic design, narrative strategy, and creative intelligence workflows.
    12
    9
    1
    MIT

  • Creative Ideation MCP Server

    creating-cat
    A
    license
    Not graded
    quality
    C
    maintenance
    Utilizes the Google Gemini API to generate context-specific categories and diverse options for creative brainstorming. It features a random sampling function to help users bypass predictable AI patterns and discover unexpected, innovative ideas.
    32
    1
    MIT

  • Scryfall MCP Server

    JoeMoCode
    A
    license
    A
    quality
    C
    maintenance
    Enables Claude to search and retrieve Magic: The Gathering card details, prices, set information, and random cards from Scryfall's database through natural language.
    4
    2
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lmorchard/oblique-strategies-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server