PluginBench
MCP Server

io.github.volsier/memforge-memory MCP Server

io.github.volsier/memforge-memory

Registry
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 io.github.volsier/memforge-memory MCP server?

Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.

How to install io.github.volsier/memforge-memory

Copy-paste configuration for popular MCP clients.

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

    PostgreSQL connection string

  • OPENAI_BASE_URL
    required

    Embedding API base URL (OpenAI-compatible)

  • OPENAI_API_KEY
    required
    secret

    Embedding API key

  • OPENAI_EMBEDDING_MODEL
    required

    Embedding model name (e.g. BAAI/bge-m3)

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "memforge-memory": {
      "command": "npx",
      "args": [
        "-y",
        "@memforgeai/memory-service"
      ],
      "env": {
        "DATABASE_URL": "<YOUR_DATABASE_URL>",
        "OPENAI_BASE_URL": "<YOUR_OPENAI_BASE_URL>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "OPENAI_EMBEDDING_MODEL": "<YOUR_OPENAI_EMBEDDING_MODEL>"
      }
    }
  }
}

Related MCP servers

Split a task into plans with disjoint file boundaries; scaffold a git worktree per plan.

0
TypeScript
MIT
View repository →
MIMidas logo

Midas

Active

Local-first agent memory that persists across sessions—no LLM at ingest, fully offline, $0 per message.

13
Python
MIT
View repository →

MCP server for Ansys engineering simulations — CFD, FEA, meshing, and post-processing. 24 tools.

VOVouch logo

Vouch

Active

Git-native, review-gated knowledge base for LLM agents with cited retrieval and audited writes.

112
Python
MIT
View repository →

Persistent shopping memory for AI assistants. The AI reasons; Kaufliste stores and executes.

View repository →

Shared per-repo space for Claude Code sessions: see activity, get collision warnings, notes.

0
TypeScript
MIT
View repository →