Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AUTO_LINKNoEnable automatic entity linking in knowledge graphtrue
LOG_LEVELNoSet logging level (debug, info, warn, error)info
MCP_DEBUGNoEnable debug loggingfalse
TOOL_LIMITNoMaximum number of tool calls per session25
EXA_API_KEYYesAPI key for Exa web search (required for exa_search and exa_answer tools)
MEMORY_PATHNoPath to the memory storage file~/.mcp-think-tank/memory.jsonl
MCP_LOG_FILENoEnable/disable file loggingtrue
CACHE_CONTENTNoEnable/disable content-based caching for file/URL operationstrue
MCP_LISTEN_PORTNoSet custom port for MCP server3399
TOOL_CACHE_SIZENoMaximum number of cached tool calls100
CACHE_TOOL_CALLSNoEnable/disable duplicate tool call cachingtrue
CONTENT_CACHE_TTLNoTime-to-live for cached content in milliseconds300000
CONTENT_CACHE_SIZENoMaximum number of items in content cache50
MAX_OPERATION_TIMENoMaximum time for batch operations in milliseconds5000
MIN_SIMILARITY_SCORENoThreshold for entity matching0.85

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
upsert_entitiesC

Create new entities or update existing ones in the knowledge graph using an upsert pattern

create_relationsC

Create multiple new relations between entities in the knowledge graph. Relations should be in active voice

add_observationsC

Add new observations to existing entities in the knowledge graph

delete_entitiesC

Delete multiple entities and their associated relations from the knowledge graph

delete_observationsC

Delete specific observations from entities in the knowledge graph

delete_relationsC

Delete multiple relations from the knowledge graph

read_graphC

Read the entire knowledge graph

search_nodesC

Search for nodes in the knowledge graph based on a query

open_nodesC

Open specific nodes in the knowledge graph by their names

update_relationsC

Update multiple existing relations in the knowledge graph

memory_queryC

Query the memory store with advanced filters

thinkA

Use the tool to think about something. It will not obtain new information or change the database, but just append the thought to the log. Use it when complex reasoning or some cache memory is needed. Consider including: problem definition, relevant context, analysis steps, self-reflection on your reasoning, and conclusions. Adapt this structure as needed for your specific thought process.

plan_tasksC

Create multiple tasks from a plan. Generates IDs and syncs with knowledge graph.

list_tasksC

List tasks with optional filtering by status and priority.

next_taskA

Get the next highest priority todo task and mark it as in-progress.

complete_taskC

Mark a task as completed.

update_tasksC

Update multiple tasks with new values.

show_memory_pathA

Return absolute path of the active knowledge-graph file.

exa_searchC

Search the web using Exa API

exa_answerC

Ask a question and get a sourced answer via Exa /answer API.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
Health

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/flight505/mcp-think-tank'

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