Skip to main content
Glama

Advanced Reasoning MCP Server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Schema

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Tools

Functions exposed to the LLM to take actions

NameDescription
advanced_reasoning

Advanced cognitive reasoning tool that builds on sequential thinking with meta-cognition, hypothesis testing, and integrated memory.

Key Features:

  • Meta-cognitive assessment and confidence tracking
  • Hypothesis formulation and testing capabilities
  • Integrated graph-based memory system
  • Dynamic reasoning quality evaluation
  • Session-based context management
  • Evidence tracking and validation

Enhanced Parameters:

  • thought: Your reasoning step (required)
  • thoughtNumber/totalThoughts: Sequential tracking (required)
  • nextThoughtNeeded: Continue flag (required)
  • confidence: Self-assessment 0.0-1.0 (default: 0.5)
  • reasoning_quality: 'low'|'medium'|'high' (default: 'medium')
  • meta_thought: Reflection on your reasoning process
  • hypothesis: Current working hypothesis
  • test_plan: How to validate the hypothesis
  • test_result: Outcome of testing
  • evidence: Supporting/contradicting evidence
  • session_id: Link to reasoning session
  • goal: Overall objective
  • progress: 0.0-1.0 completion estimate

Branching (inherited from sequential thinking):

  • isRevision/revisesThought: Revise previous thoughts
  • branchFromThought/branchId: Explore alternatives

Use this tool for complex reasoning that benefits from:

  • Self-reflection and confidence tracking
  • Systematic hypothesis development
  • Memory of previous insights
  • Quality assessment of reasoning
query_reasoning_memory

Query the integrated memory system to find related insights, hypotheses, and evidence.

Useful for:

  • Finding similar problems solved before
  • Retrieving relevant hypotheses and evidence
  • Understanding connections between ideas
  • Building on previous reasoning sessions

Parameters:

  • session_id: The reasoning session to query within (required)
  • query: What to search for in memory (required)

Returns related memories with confidence scores and connection information.

create_memory_library

Create a new named memory library for organized knowledge storage.

Enables you to create separate, named memory libraries for different projects, domains, or contexts. Library names must contain only letters, numbers, underscores, and hyphens.

Parameters:

  • library_name: Name for the new library (required)

Returns success status and message.

list_memory_libraries

List all available memory libraries with metadata.

Shows all existing memory libraries with information about:

  • Library name
  • Number of memory nodes
  • Last modified date

Returns organized, searchable library information.

switch_memory_library

Switch to a different memory library.

Allows you to switch between different memory libraries for different contexts or projects. Current session state is saved before switching.

Parameters:

  • library_name: Name of the library to switch to (required)

Returns success status and message.

get_current_library_info

Get information about the currently active memory library.

Shows current library name, number of nodes, sessions, and other metadata.

Returns current library information.

create_system_json

Create a new system JSON file for storing coherent detailed searchable data or instructions and workflows for any domain or action.

Parameters:

  • name: Name for the system JSON file (required) - alphanumeric, underscore, hyphen only
  • domain: Domain or category for the data (required)
  • description: Description of what this system JSON contains (required)
  • data: The structured data to store (required) - can be any JSON-serializable object
  • tags: Optional array of tags for searchability

Returns success status and confirmation message.

get_system_json

Retrieve a system JSON file by name.

Parameters:

  • name: Name of the system JSON file to retrieve (required)

Returns the complete system JSON data including metadata and content.

search_system_json

Search through system JSON files by query.

Parameters:

  • query: Search query to find matching system JSON files (required)

Returns matching files with relevance scores.

list_system_json

List all available system JSON files.

Returns list of all system JSON files with their names, domains, and descriptions.

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/angrysky56/advanced-reasoning-mcp'

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