MCP Servers · apify

mcpc

mcpc is a universal CLI client for the Model Context Protocol that enables AI agents and users to interact with MCP servers through shell commands. It supports persistent sessions, OAuth 2.1 authentication, tool/resource/prompt discovery, and integrates MCP capabilities into standard Unix pipelines.

Talk to DEV.co Discuss Implementation

Source: GitHub — github.com/apify/mcpc

709

GitHub stars

Forks

TypeScript

Primary language

Apache-2.0

License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

Field	Value
Repository	apify/mcpc
Owner	apify
Primary language	TypeScript
License	Apache-2.0 — OSI-approved
Stars	709
Forks	66
Open issues	12
Latest release	v0.4.0 (2026-06-25)
Last updated	2026-07-04
Source	https://github.com/apify/mcpc

What mcpc is

TypeScript-based CLI that implements full MCP support (tools, prompts, resources, tasks, skills, logging) over stdio and HTTP transports. Features include session persistence, OAuth 2.1 with CIMD/DCR, OS keychain integration for credential storage, JSON output mode for scripting, and experimental x402 payment protocol support.

Quickstart

Get the mcpc source

Clone the repository and explore it locally.

terminalbash

1git clone https://github.com/apify/mcpc.git2cd mcpc3# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

AI Agent Shell Integration

Provide AI agents with MCP access through a single Bash tool, eliminating the need to wire up dozens of MCP functions while maintaining token efficiency and reliable tool discovery.

Interactive MCP Server Debugging

Manually inspect, test, and debug MCP servers using intuitive CLI commands that map directly to MCP operations, with persistent sessions and JSON output for analysis.

Shell-Based MCP Workflow Automation

Compose repeatable MCP workflows as shell scripts using standard Unix pipes, jq, and xargs, with credential sharing across multiple agents on the same machine.

Implementation considerations

Requires Node.js or Bun installation; verify runtime availability in target deployment environment.
Linux systems need explicit keychain setup (libsecret/gnome-keyring) or must accept file-based credential storage with appropriate permissions.
OAuth 2.1 profiles are stored per machine; sharing credentials across agents requires co-location or centralized credential management.
Session state is kept in memory; sessions are lost on restart unless persisted via explicit configuration.
Timeout defaults to 60 seconds; adjust via --timeout flag for long-running MCP operations.

When to avoid it — and what to weigh

Graphical UI Requirement — If your use case requires a graphical interface or dashboard, mcpc is CLI-only and does not provide web or desktop UI alternatives.
No JavaScript Runtime Available — mcpc requires Node.js or Bun runtime. Environments without JavaScript support (e.g., pure Python/Go stacks) cannot run mcpc natively.
Headless Credential Storage Without Configuration — Linux headless/CI systems require either libsecret/gnome-keyring setup or acceptance of file-based credential storage (~/.mcpc/credentials) instead of OS keychain.
MCP Server Development (Not a Server) — mcpc is a client only. If you need to build or host MCP servers, you need separate server libraries and infrastructure.

License & commercial use

Apache License 2.0 (Apache-2.0). Permissive OSI-approved license allowing commercial use, modification, and distribution with minimal restrictions.

Apache-2.0 permits commercial use, including proprietary deployments and SaaS offerings, provided the license and copyright notice are retained. No restrictions on closed-source derivatives. Suitable for commercial integration.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

Signal	Assessment
Maintenance	Active
Documentation	Strong
License clarity	Clear
Deployment complexity	Low
DEV.co fit	Strong
Assessment confidence	High

Security considerations

Supports OAuth 2.1 with CIMD and DCR for secure remote authentication. Uses OS keychain (macOS/Windows) or file-based storage (0600 perms, Linux) for credentials. Offers TLS certificate verification (--insecure flag bypasses for self-signed certs). Proxy mode isolates MCP credentials from untrusted AI-generated code. No assertions of cryptographic strength or formal audit available from provided data.

Alternatives to consider

Anthropic Claude API with native MCP support

If deploying only with Claude, native MCP support in Claude API may reduce need for a separate CLI bridge, though mcpc offers broader agent compatibility.

Direct HTTP API wrappers (custom)

Custom HTTP wrappers around MCP servers avoid CLI dependency but sacrifice standardization, credential sharing, and shell composability.

MCP server SDKs (e.g., Anthropic's mcp-sdk-ts)

Building custom agents directly against MCP SDKs provides full control but requires more engineering effort and cannot share sessions across agents.

Software development agency

Build on mcpc with DEV.co software developers

Install mcpc via npm and connect your first MCP server in minutes. Perfect for integrating MCP into AI agent workflows.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

apify-mcp-server mcp mcp-client-cli

Related on DEV.co

Explore the category and the services that help you build with it.

MCP Servers AI Development API Development Cloud Deployment Talk to DEV.co

mcpc FAQ

Can I use mcpc with any MCP server?

Yes. mcpc supports any MCP-compliant server over stdio or HTTP. Configuration can reference local packages (.vscode/mcp.json:entry) or remote URLs (mcp.apify.com).

How do I share mcpc sessions between multiple AI agents?

All agents on the same machine can reference the same @session name after one agent has connected. Credentials are stored in OS keychain or file storage and reused across agents.

What happens if a session crashes?

Use mcpc restart <@session> to reconnect without losing state (if server supports it) or mcpc close <@session> to terminate and reconnect fresh.

Is mcpc suitable for production AI agent deployments?

Yes, if deployed on machines with proper credential management (OS keychain or secure file storage) and network access to MCP servers. Consider using the proxy feature to isolate untrusted code.

Software developers & web developers for hire

From first prototype to production, DEV.co delivers software development services around tools like mcpc. Our software development agency staffs experienced software developers and web developers for custom software development, web development, integrations, and ongoing support across mcp servers and beyond.

Get Started with mcpc

Install mcpc via npm and connect your first MCP server in minutes. Perfect for integrating MCP into AI agent workflows.

Talk to DEV.co Schedule a Consultation