Skip to main content
Glama
j0hanz

cortex-mcp

by j0hanz
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CORTEX_MAX_SESSIONSNoMaximum number of active sessions100
CORTEX_SESSION_TTL_MSNoSession time-to-live in milliseconds (default 30 minutes)1800000
CORTEX_MAX_TOTAL_TOKENSNoMaximum total tokens across all sessions2000000
CORTEX_REDACT_TRACE_CONTENTNoWhether to redact trace contentfalse
CORTEX_MAX_ACTIVE_REASONING_TASKSNoMaximum number of active reasoning tasks32

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": true
}
resources
{
  "listChanged": true
}
completions
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
reasoning_thinkA

Structured multi-step reasoning tool. Decomposes analysis into sequential thought steps stored in a persistent session trace.

USAGE PATTERN:

  1. Start: { query: "...", level: "basic"|"normal"|"high"|"expert", thought: "your analysis..." }

  2. Continue: { sessionId: "", thought: "next step..." } — level is optional; session level is used

  3. Repeat until status: "completed" — the summary field contains the exact next call to make

IMPORTANT: Pass the returned sessionId on every continuation call. The thought parameter stores YOUR reasoning verbatim — write thorough analysis in each step. Use stepSummary for a 1-sentence conclusion per step — these accumulate in the summary field for navigation.

Levels: basic (1–3 steps, 2K budget), normal (4–8 steps, 8K budget), high (10–15 steps, 32K budget), expert (20–25 steps, 128K budget). Alternatives: runMode="run_to_completion" (batch, basic level only), or observation/hypothesis/evaluation fields (structured). Errors: E_SESSION_NOT_FOUND (expired — start new), E_INVALID_THOUGHT_COUNT (check level ranges).

Prompts

Interactive templates invoked by user choice

NameDescription
reasoning.basicBasic-depth reasoning (1-3 thoughts).
reasoning.normalNormal-depth reasoning (4-8 thoughts).
reasoning.highHigh-depth reasoning (10-15 thoughts).
reasoning.expertExpert-depth reasoning (20-25 thoughts).
reasoning.retryRetry a failed reasoning task with modified parameters.
get-helpReturn server usage instructions.
reasoning.continueContinue an existing session. Optional follow-up query.

Resources

Contextual data attached and managed by the client

NameDescription
server-instructionsUsage instructions for the MCP server.
tool-catalogTool reference: models, params, outputs, data flow.
workflowsRecommended workflows and tool sequences.
server-configRuntime limits and level configurations for the reasoning server.
reasoning.sessionsList of active reasoning sessions with summaries. Updated in real-time as sessions progress.
tool-info-reasoning_thinkContract details for reasoning_think.

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/j0hanz/cortex-mcp'

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