Developer · Local MCP server

Contextful

Efficient context management: code search, evidence packs, and memory for coding agents.

Visit Contextful's website

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.Inferensys/contextful
Version
0.1.0
Status
Active
Category
developer
Transport
stdio (local process)
Package
npm
Published
2026-05-15
Updated
2026-05-15
Publisher
Inferensys (GitHub) · 2 servers with pages here
Website
inferensys.github.io/contextful/
Repository
github.com/Inferensys/contextful
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
npm@inferensys/contextful0.1.0stdioNone declared

How to connect Contextful

Contextful runs locally from a Node.js package published to the npm registry: @inferensys/contextful version 0.1.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @inferensys/contextful@0.1.0.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "contextful": {
      "command": "npx",
      "args": [
        "-y",
        "@inferensys/contextful@0.1.0"
      ]
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from Inferensys (GitHub)

ServerRunsEndpoint or package
dr-mcpAudits MCP configs, scores risk, and creates reversible repair plans.Local · stdionpm: @inferensys/dr-mcp

More developer servers

All 6,250 →
ServerRunsEndpoint or package
ContextatlasPre-computed atlas of your codebase for Claude Code: LSP + ADRs + git. 45-72% token reduction.Local · stdionpm: contextatlas
ContextBridgeMCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.Local · stdioNuGet: ThunderEagle.ContextBridge
contextburnRun efficiency for coding agents: share of paid tokens that became output, not context re-reading.Local · stdioPyPI: contextburn
Contextforge MCPPersistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.Local · stdionpm: contextforge-mcp
contextkeeperZero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.Local · stdioPyPI: contextkeeper
ContextLibA project's long-term memory as plain Markdown files, with an append-only, tamper-evident log.Local · stdioOCI image (Docker): ghcr.io/willykeenan/agentbrain-contextlib:0.1.0
ContextStreamPersistent memory and cross-session learning for AI coding assistants (hosted remote MCP).Remote · HTTPmcp.contextstream.io
ContextStream MCP ServerProject memory, semantic code search, and grounded agent context.Remote & Local · HTTP, stdiomcp.contextstream.io