Skip to main content
Glama
manasp21

Event Horizon MCP Server

by manasp21
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Hybrid

Event Horizon MCP Server

Smithery License: MIT TypeScript

An MCP server implementation that provides evolutionary solution generation and optimization capabilities for LLMs. Event Horizon enables LLMs to evolve solutions across multiple generations using consistency check evaluations and genetic algorithm principles.

Features

  • Multi-generational Evolution: Evolve solutions across multiple generations

  • Consistency Check Evaluation: Score solutions against multiple criteria

  • Crossover Analysis: Identify best aspects from different solutions

  • Convergence Detection: Automatically detect when solutions reach optimal scores

  • Progress Tracking: Monitor evolution progress and statistics

  • Flexible Configuration: Customize population size, generations, and thresholds

Related MCP server: GEPA MCP Server

How It Works

  1. Initialize Evolution: Define a problem statement and consistency checks

  2. Generate Population: Create initial solutions for generation 0

  3. Evaluate Solutions: Score each solution against all consistency checks

  4. Evolution Analysis: Identify best-performing aspects per consistency check

  5. Crossover Guidance: Get recommendations for combining best aspects

  6. Next Generation: Create new solutions based on crossover recommendations

  7. Repeat: Continue until convergence or max generations reached

Tools

start_evolution

Initialize an evolutionary solution system with a problem and consistency checks.

Parameters:

  • problemStatement (string): The problem or challenge to solve

  • consistencyChecks (array): Array of evaluation criteria (strings or objects with description/weight)

  • populationSize (integer, optional): Solutions per generation (default: 3)

  • maxGenerations (integer, optional): Maximum generations (default: 5)

  • convergenceThreshold (number, optional): Score threshold for completion (default: 0.95)

add_solution

Add a new solution to the current generation.

Parameters:

  • content (string): The solution content addressing the problem

  • parentSolutions (array, optional): Parent solution IDs if this is a crossover

score_solution

Score a solution against a specific consistency check.

Parameters:

  • solutionId (string): ID of the solution to score

  • checkId (string): ID of the consistency check

  • score (number): Score between 0.0 and 1.0

  • reasoning (string, optional): Explanation of the scoring rationale

evolve_generation

Evolve to the next generation using crossover analysis.

Returns crossover recommendations identifying the best-performing solution for each consistency check and guidance for creating new solutions.

get_evolution_status

Get the current status of the evolutionary system including progress, statistics, and best solution found.

Installation

Smithery (Recommended)

Install directly from the Smithery registry for the easiest setup:

npx @smithery/cli install event-horizon --client claude

This automatically configures the server for Claude Desktop. You can also customize the installation:

npx @smithery/cli install event-horizon --client claude --config '{"disableLogging": true, "populationSize": 5}'

Manual Installation

If you prefer manual installation, add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "event-horizon": {
      "command": "node",
      "args": [
        "/path/to/EventHorizon/dist/index.js"
      ]
    }
  }
}

Clone and Build

For development or customization:

git clone https://github.com/manasp21/EventHorizon.git
cd EventHorizon
npm install
npm run build

Advanced Configuration

Configuration Options

The Event Horizon server supports several configuration options:

  • disableLogging (boolean): Disable evolution progress logging (default: false)

  • populationSize (integer): Default population size for generations (default: 3)

  • maxGenerations (integer): Default maximum generations (default: 5)

  • convergenceThreshold (number): Default convergence threshold (default: 0.95)

Docker

Build and run with Docker:

docker build -t event-horizon-mcp .
docker run --rm -i event-horizon-mcp

Or use in Claude Desktop config:

{
  "mcpServers": {
    "event-horizon": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "event-horizon-mcp"
      ]
    }
  }
}

VS Code & Other MCP Clients

For other MCP clients, you can use Smithery CLI or manual configuration. Check the Smithery documentation for client-specific instructions.

Usage Example

Here's a typical evolutionary workflow:

1. Start Evolution

{
  "tool": "start_evolution",
  "arguments": {
    "problemStatement": "Design an efficient sorting algorithm",
    "consistencyChecks": [
      "Algorithm must have optimal time complexity",
      "Implementation must be memory efficient",
      "Code must be readable and maintainable"
    ],
    "populationSize": 3,
    "maxGenerations": 5
  }
}

2. Add Initial Solutions

{
  "tool": "add_solution",
  "arguments": {
    "content": "Implement quicksort with random pivot selection..."
  }
}

3. Score Solutions

{
  "tool": "score_solution",
  "arguments": {
    "solutionId": "generated_solution_id",
    "checkId": "check_1",
    "score": 0.8
  }
}

4. Evolve Generation

{
  "tool": "evolve_generation",
  "arguments": {}
}

The system will provide crossover recommendations like:

{
  "crossoverRecommendations": [
    {
      "checkId": "check_1",
      "bestSolutionId": "solution_a",
      "score": 0.9,
      "relevantContent": "Use random pivot selection for optimal performance..."
    }
  ]
}

5. Create Next Generation

Based on recommendations, create new solutions combining the best aspects from previous generation.

Environment Variables

  • DISABLE_EVOLUTION_LOGGING: Set to "true" to disable progress logging

Building

npm run build
npm run prepare

Docker

docker build -t mcp/event-horizon -f Dockerfile .

Example Use Cases

  • Algorithm Design: Evolve optimal algorithms for specific problems

  • Code Optimization: Improve code performance across multiple metrics

  • Creative Writing: Evolve stories or content meeting multiple criteria

  • Problem Solving: Generate solutions optimized for multiple constraints

  • System Design: Evolve architectural solutions balancing various requirements

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License.

Available Tools

5 tools
add_solutionA

Add a new solution to the current generation of the evolutionary system.

Use this tool to contribute solutions to the current generation. Solutions can be:

  • Initial solutions (generation 0)

  • Evolved solutions based on crossover recommendations

  • Variations or mutations of existing solutions

The solution content should directly address the problem statement.

ParametersJSON Schema
NameRequiredDescriptionDefault
contentYesThe solution content addressing the problem statement
parentSolutionsNoOptional array of parent solution IDs if this is a crossover

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden. It clarifies that solutions are added to the 'current generation' and mentions different types of solutions, but doesn't disclose behavioral traits like whether this is a mutation operation, what permissions are needed, how solutions are stored, or what happens on failure. The description adds some context but 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 well-structured with a clear opening statement followed by bullet points for use cases and a final requirement statement. Every sentence earns its place, and there's no wasted text. It's appropriately sized for the tool's complexity.

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 no annotations and no output schema, the description provides adequate basic context but lacks completeness. It explains what the tool does and when to use it, but doesn't cover important aspects like what the tool returns, error conditions, or system behavior after adding a solution. For a mutation tool with 2 parameters, more completeness would be expected.

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

Parameters3/5

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 both parameters thoroughly. The description adds marginal value by emphasizing that 'solution content should directly address the problem statement' for the content parameter, but doesn't provide additional semantics beyond what the schema descriptions already state.

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 action ('Add a new solution') and resource ('to the current generation of the evolutionary system'), distinguishing it from siblings like evolve_generation or score_solution. However, it doesn't explicitly differentiate from start_evolution which might also involve adding initial solutions.

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 contribute solutions to the current generation') and lists three specific use cases (initial solutions, evolved solutions, variations). It doesn't explicitly state when NOT to use it or name alternatives among siblings, but the context is sufficiently clear.

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

evolve_generationA

Evolve to the next generation using crossover analysis.

This tool analyzes the current generation's performance and provides crossover recommendations. It identifies the best-performing solution for each consistency check and suggests how to combine these aspects into new solutions for the next generation.

Use this after all solutions in the current generation have been fully scored.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4/5.0
Behavior3/5

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 describes the tool's behavior (analyzes performance, provides crossover recommendations, identifies best solutions, suggests combinations), but lacks details on side effects, error conditions, or output format. For a tool with no annotations, this is a moderate but incomplete disclosure.

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 well-structured and concise: a brief purpose statement followed by elaboration and a clear usage instruction. Every sentence adds value without redundancy, and it's front-loaded with the core function.

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 complexity (evolutionary analysis with no parameters) and lack of annotations/output schema, the description covers purpose and usage well but omits details on what the tool returns or how failures are handled. It's adequate for basic understanding but leaves gaps for robust agent operation.

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 input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, focusing instead on the tool's function and usage context. A baseline of 4 is applied since no parameters exist to document.

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: 'Evolve to the next generation using crossover analysis' and elaborates on analyzing performance and providing recommendations. It distinguishes from siblings like 'add_solution' or 'score_solution' by focusing on generation evolution, though it doesn't explicitly contrast with 'get_evolution_status' or 'start_evolution'.

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

Usage Guidelines5/5

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

The description provides explicit usage guidance: 'Use this after all solutions in the current generation have been fully scored.' This clearly indicates when to invoke the tool relative to other operations, helping the agent sequence actions correctly without needing trial and error.

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

get_evolution_statusA

Get the current status of the evolutionary system.

Returns detailed information about the current state including:

  • Current generation and progress

  • Population statistics

  • Best solution found so far

  • Evolution history

Use this tool to track progress and understand the current state of the evolution.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.4/5.0
Behavior3/5

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 describes what information is returned (generation progress, population statistics, best solution, evolution history) which is valuable context. However, it doesn't mention potential limitations like whether this requires specific permissions, if there are rate limits, or what format the data is returned in.

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 perfectly structured and concise. It opens with the core purpose, lists the specific information returned in a clear bullet format, and ends with explicit usage guidance. Every sentence earns its place with no wasted words or redundancy.

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 zero-parameter status-checking tool with no output schema, the description provides excellent context about what information is returned. The main gap is the lack of output format details (structure, data types), but given the tool's relative simplicity and clear purpose, the description is nearly complete for agent understanding.

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 zero parameters, and schema description coverage is 100% (though trivial since there are no parameters). The description appropriately doesn't discuss parameters since none exist, which is correct for a zero-parameter tool. No additional parameter information is needed or provided.

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 verb ('Get') and resource ('current status of the evolutionary system'), distinguishing it from sibling tools like 'add_solution', 'evolve_generation', 'score_solution', and 'start_evolution' which perform different operations. It explicitly identifies this as a monitoring/status-checking tool rather than an action tool.

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

Usage Guidelines5/5

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

The description provides explicit usage guidance: 'Use this tool to track progress and understand the current state of the evolution.' This clearly indicates when to use this tool (for monitoring) versus when to use sibling tools for performing evolutionary operations like adding solutions or evolving generations.

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

score_solutionB

Score a solution against a specific consistency check.

Use this tool to evaluate how well a solution performs against each consistency check. Scores should be between 0.0 (poor) and 1.0 (excellent).

The LLM should evaluate the solution content against the consistency check description and provide an objective score.

ParametersJSON Schema
NameRequiredDescriptionDefault
solutionIdYesID of the solution to score
checkIdYesID of the consistency check to evaluate against
scoreYesScore between 0.0 and 1.0
reasoningNoOptional explanation of the scoring rationale

TDQS

B3.2/5.0
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 mentions that 'The LLM should evaluate the solution content against the consistency check description and provide an objective score,' which hints at an evaluation process, but doesn't disclose critical behavioral traits such as whether this is a read-only operation, if it modifies data, what permissions are required, or how the scoring interacts with other tools. For a tool with no annotations, this leaves significant gaps in understanding its behavior.

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 stated in the first sentence. It uses three sentences efficiently: the first defines the tool, the second provides usage context and score range, and the third adds behavioral guidance. There's minimal waste, though the third sentence could be more integrated for slightly better flow.

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 complexity (a scoring tool with 4 parameters), no annotations, and no output schema, the description is moderately complete. It covers the basic purpose and usage but lacks details on behavioral aspects, return values, or how it fits with sibling tools. For a tool that likely involves evaluation logic, more context on the scoring process or output expectations would improve completeness, but it's adequate as a minimum viable description.

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

Parameters3/5

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

The input schema has 100% description coverage, with clear documentation for all parameters (solutionId, checkId, score, reasoning). The description adds minimal value beyond the schema: it reinforces the score range (0.0 to 1.0) and mentions 'objective score,' but doesn't provide additional semantics like examples or context for the IDs. With high schema coverage, the baseline score of 3 is appropriate as the schema does the heavy lifting.

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: 'Score a solution against a specific consistency check' and 'evaluate how well a solution performs against each consistency check.' It specifies the verb ('score', 'evaluate') and resource ('solution', 'consistency check'), but doesn't explicitly differentiate from sibling tools like 'add_solution' or 'evolve_generation', which appear to be related but distinct operations.

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 provides implied usage context: 'Use this tool to evaluate how well a solution performs against each consistency check.' It suggests when to use it (for scoring solutions against checks) but doesn't explicitly state when not to use it or mention alternatives among the sibling tools, leaving some ambiguity about its specific role in the workflow.

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

start_evolutionA

Initialize an evolutionary solution system for a given problem with consistency checks.

This tool sets up the framework for evolving solutions across multiple generations. The LLM will:

  1. Generate initial population of solutions

  2. Evaluate solutions against consistency checks

  3. Use crossover recommendations to create better solutions

  4. Repeat until convergence or max generations

Use this tool to begin the evolutionary process with a clear problem statement and evaluation criteria.

ParametersJSON Schema
NameRequiredDescriptionDefault
problemStatementYesThe problem or challenge to solve
consistencyChecksYesArray of consistency checks (strings or objects with description and weight)
populationSizeNoNumber of solutions per generation (default: 3)
maxGenerationsNoMaximum number of generations (default: 5)
convergenceThresholdNoScore threshold for convergence (default: 0.95)

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden. It explains the multi-step process (generate, evaluate, crossover, repeat) which is valuable behavioral context. However, it doesn't disclose important traits like whether this is a long-running operation, what happens if interrupted, or what permissions might be required.

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 with 5 sentences. It's front-loaded with the core purpose, then details the process, and ends with usage guidance. The bullet-point style for the process steps is efficient, though the final sentence could be more concise.

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?

For a complex initialization tool with no annotations and no output schema, the description provides good process context but lacks details about what the tool returns, error conditions, or system requirements. It covers the 'what' and 'why' adequately but misses some operational details an agent would need.

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

Parameters3/5

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 mentions 'problem statement and evaluation criteria' which maps to the required parameters, but doesn't add significant meaning beyond what the schema already provides about each parameter's purpose.

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 tool's purpose: 'Initialize an evolutionary solution system for a given problem with consistency checks.' It specifies the verb ('Initialize'), resource ('evolutionary solution system'), and distinguishes from siblings by focusing on setup rather than ongoing operations like add_solution or evolve_generation.

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: 'Use this tool to begin the evolutionary process with a clear problem statement and evaluation criteria.' It implies this is the starting point, but doesn't explicitly state when NOT to use it or name specific alternatives among the siblings.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose in the evolutionary workflow: start_evolution initializes the system, add_solution contributes solutions, score_solution evaluates them, evolve_generation advances to the next generation, and get_evolution_status monitors progress. There is no overlap or ambiguity between these functions.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (e.g., start_evolution, add_solution, score_solution, evolve_generation, get_evolution_status). The naming is uniform, predictable, and clearly describes each tool's action and target.

Tool Count5/5

With 5 tools, the server is well-scoped for its evolutionary solution domain. Each tool earns its place by covering essential steps: initialization, solution management, scoring, evolution, and status tracking. This count is neither too sparse nor bloated.

Completeness5/5

The tool set provides complete coverage of the evolutionary lifecycle: start_evolution sets up the system, add_solution handles solution input, score_solution evaluates them, evolve_generation progresses iterations, and get_evolution_status offers monitoring. There are no obvious gaps for core operations.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

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

  • GEPA MCP Server

    developzir
    A
    license
    Not graded
    quality
    D
    maintenance
    Implements the Genetic-Evolutionary Prompt Architecture for automatic prompt optimization, providing tools to optimize, quickly improve, and contextually adapt prompts.
    51
    MIT

  • genetic-mcp

    andrasfe
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables evolutionary idea generation using genetic algorithms with LLM workers, multi-objective fitness evaluation, and advanced genetic operations.
    1
    MIT

  • self-consistency-engine

    SanjoyDat1
    -
    license
    Not graded
    quality
    Not graded
    maintenance
    Enables chain-of-thought reasoning with self-consistency voting, allowing sampling of diverse reasoning paths and aggregating answers via majority or weighted vote for improved accuracy.

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/manasp21/EventHorizon'

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