PluginBench
MCP Server
Active
MIT

Inkwell MCP Server

io.github.veronchenko/inkwell-memory

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 Inkwell MCP server?

Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links

How to install Inkwell

Copy-paste configuration for popular MCP clients.

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

    Knowledge base root inside the container; matches the volume mount target

  • INKWELL_ENABLE_DASHBOARD

    Set to 0 to skip the web dashboard process and run the MCP server only

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "inkwell-memory": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/foreigndmitryi/inkwell-memory:0.14.0",
        "-v",
        "{knowledge_path}:/knowledge"
      ],
      "env": {
        "INKWELL_DATA_PATH": "<YOUR_INKWELL_DATA_PATH>",
        "INKWELL_ENABLE_DASHBOARD": "<YOUR_INKWELL_ENABLE_DASHBOARD>"
      }
    }
  }
}

Related MCP servers

MCMCP AutoMem logo

Graph-vector memory for AI assistants with persistent recall across Claude, Cursor, and other MCP platforms.

63
TypeScript
MIT
View repository →

Prediction market intelligence for AI agents. Live data from Kalshi and Polymarket.

0
TypeScript
View repository →
AGAgentBase logo

AgentBase

Maintained

Shared knowledge base for AI agents. Semantic search across agents, no setup required — just a URL.

2
TypeScript
MIT
View repository →

Generate, edit and upscale AI video and images from any agent via VicSee.

0
TypeScript
MIT
View repository →

Charter-bound defensive security copilot: secrets, obfuscation, deps, Dockerfile, IaC scans.

View repository →
VEVersion Pill logo

Version Pill

Maintained

Product management, public changelog, and feature requests - 60 lean MCP tools.

0
View repository →