ejentum-mcp
Reasoning, code, anti-deception, memory harness MCP tools. Stdio or HTTPS api.ejentum.com/mcp
Should I use this
Quality & Safety
Findings (1)
- LOWTool 'ejentum_graph' description lacks action verbin ejentum_graph
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"ejentum-mcp": {
"command": "npx",
"args": [
"ejentum-mcp"
]
}
}
}Runnable packages
0.2.2stdioRemote endpoints
https://api.ejentum.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (4)
🟢ejentum_scaffold(query, mode, stack_size)
Retrieve a deterministic reasoning scaffold (Reasoning-Augmented Retrieval) to prevent hallucinations, causal inversion, and compounding multi-step failures.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The user task, error trace, or diagnostic question to analyze."
},
"mode": {
"type": "string",
"enum": [
"single",
"stack",
"graph"
],
"default": "single",
"description": "Reasoning mode: 'single' (Top-1 focused invariant), 'stack' (multi-tier synthesis), or 'graph' (synergy DAG traversal)."
},
"stack_size": {
"type": "integer",
"default": 2,
"description": "Number of complementary cognitive dimensions to stack (1-4)."
}
},
"required": [
"query"
]
}🟢ejentum_domains
List the 6 invariant cognitive failure dimensions and primary failure modes mapped by Ejentum.
Input Schema
{
"type": "object",
"properties": {}
}⚪ejentum_graph(query, ability_id, depth)
Traverse the 933-edge cognitive synergy graph to compose a multi-hop Cognitive Directed Acyclic Graph (DAG) with Root, Prerequisite, Amplifier, and Fallback operators.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The complex task, system failure, or architecture question to analyze."
},
"ability_id": {
"type": "string",
"description": "Optional specific root ability ID (e.g. 'CA-001', 'SI-039') to traverse directly."
},
"depth": {
"type": "integer",
"enum": [
1,
2
],
"default": 1,
"description": "Graph traversal depth: 1 (direct 1-hop dependencies) or 2 (recursive multi-hop chaining for autonomous agent workflows)."
}
}
}🟢ejentum_fts_search(query, limit)
Execute sub-millisecond SQLite FTS5 full-text keyword search and BM25 ranking across the 311 deterministic reasoning abilities.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keyword query or search terms (e.g. 'deadlock circular dependency sequence', 'database migration')."
},
"limit": {
"type": "integer",
"default": 4,
"description": "Maximum number of abilities to return (1-10)."
}
},
"required": [
"query"
]
}Community
Evidence