Client loginBook a call
Build
Custom Software DevelopmentSystems built to your process
Web Application DevelopmentReact, Next.js, Rails, Django
Mobile App DevelopmentiOS, Android, React Native
App DevelopmentWeb and mobile apps, end to end
SaaS Product DevelopmentMulti-tenant from day one
MVP DevelopmentFirst release in 6–10 weeks
Enterprise SoftwareSSO, audit trails, scale
Connect & operate
API Development & IntegrationREST, GraphQL, webhooks
Cloud & DevOps EngineeringAWS, GCP, Azure, Terraform
QA & Software TestingAutomated suites, load, E2E
Legacy ModernizationStrangler-fig migrations
Cybersecurity EngineeringHardening and remediation
Data EngineeringPipelines, warehouses, reporting
Design & teams
UI/UX DesignInterfaces people finish tasks in
Prototyping & DiscoveryScope before you spend
Staff AugmentationSenior engineers on your team
Dedicated Dev TeamsA full pod, one contract
White-Label DevelopmentEngineering under your brand
Technology ArchitectureDecide once, correctly
Project ManagementDelivery you can audit
Start hereScope a build in one callBring a spec, a wireframe, or a paragraph. You leave with an architecture, a timeline, and a number.Book a scoping call
All software development services →How we price work →Talk to an engineer →
AI software
AI Application DevelopmentFull-stack AI products
AI Agent DevelopmentMulti-step autonomous agents
AI SaaS DevelopmentMulti-tenant AI products
Workflow AutomationReplace manual ops
Custom LLM AppsBranded internal assistants
LLM & data systems
Private LLM DevelopmentSelf-hosted Llama, Mistral, Qwen
RAG DevelopmentCited answers over your docs
MCP & WebMCPMake your systems agent-callable
Vector Database Setuppgvector, Pinecone, Qdrant
Document IntelligenceOCR and extraction pipelines
Vibe coding
AI-Assisted BuildsFast, with senior review
Rapid PrototypingClickable in days
Concept to CodeIdea to working software
Code Review & CleanupMake AI output shippable
Fractional AI TeamOngoing build capacity
Ready to ship?Put AI where the work isAgents, RAG, and private LLMs wired into the systems your team already uses — not a chatbot bolted to a homepage.Discuss an AI project
AI development services →AI readiness checklist →AI vs. traditional development →
Domain firstWe learn your workflow before we model itRegulated, operational, or high-volume — the constraints belong in the schema, not in a training doc.Talk about your domain
Selected workSoftware we own and operateMost agencies show screenshots. We run the products — the same stack, uptime, and on-call we hand to clients.View the portfolio
Plan smarterEstimate before you commitCost ranges, scope templates, and the questions we ask in discovery — free, no form.Open the cost calculator
Real conversationsTalk with a technical leadNo SDR, no discovery gauntlet. The person on the call is the one who scopes the build.Book a call
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.coDiscuss Implementation
Source: GitHub — github.com/apify/mcpc
709
GitHub stars
66
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.

FieldValue
Repositoryapify/mcpc
Ownerapify
Primary languageTypeScript
LicenseApache-2.0 — OSI-approved
Stars709
Forks66
Open issues12
Latest releasev0.4.0 (2026-06-25)
Last updated2026-07-04
Sourcehttps://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
git clone https://github.com/apify/mcpc.gitcd mcpc# 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.

SignalAssessment
MaintenanceActive
DocumentationStrong
License clarityClear
Deployment complexityLow
DEV.co fitStrong
Assessment confidenceHigh
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-servermcpmcp-client-cli

Related on DEV.co

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

MCP ServersAI Development ServicesAI DevelopmentAPI DevelopmentCloud DeploymentTalk 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.

Senior engineers for your next build

Our engineers ship mcp servers software for a living. DEV.co provides software development services, web development services, and ongoing support for teams standardizing on tools like mcpc.

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.coSchedule a Consultation