PluginBench
MCP Server
Active
MIT

Lex MCP Server

io.github.Guffawaffle/lex

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the Lex MCP server?

Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy.

How to install Lex

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • LEX_WORKSPACE_ROOT

    Root directory for the workspace. Defaults to current working directory.

  • LEX_MEMORY_DB

    Path to SQLite database file. Defaults to .smartergpt/lex/lex.db in workspace root.

  • LEX_DEBUG

    Set to any value to enable debug logging to stderr.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "lex": {
      "command": "npx",
      "args": [
        "-y",
        "@smartergpt/lex-mcp"
      ],
      "env": {
        "LEX_WORKSPACE_ROOT": "<YOUR_LEX_WORKSPACE_ROOT>",
        "LEX_MEMORY_DB": "<YOUR_LEX_MEMORY_DB>",
        "LEX_DEBUG": "<YOUR_LEX_DEBUG>"
      }
    }
  }
}

Related MCP servers

Local quantum error correction tools; decoder output verified against H c = s (mod 2).

1
Python
View repository →
GEGetABrain logo

GetABrain

Maintained

Real human judgment as agent tools — ask a question, get a structured human answer back.

0
TypeScript
MIT
View repository →
WHWhitePact logo

WhitePact

Active

AI governance MCP server: trust scoring, guardrails, bias/hallucination detection, compliance.

1
Python
MIT
View repository →

Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.

4
JavaScript
MIT
View repository →

Woody, the AI firearms expert. Verified specs, legal lookups, and knowledge base.

0
Python
MIT
View repository →
GUGuruPDF logo

GuruPDF

Active

Convert, compress & merge PDFs and 100+ file formats from any AI agent. By GuruPDF.

0
JavaScript
MIT
View repository →