Agenticorg vs Codemcp

A side-by-side look at the Agenticorg and Codemcp MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Agenticorg logoAgenticorgCoding Agents · Local subprocess (stdio)Run 25+ enterprise AI agents and 269 tools with human-in-the-loop governance63GoodAuth: not declaredCodemcp logoCodemcpCoding Agents · Local subprocess (stdio)Coding agent with basic read, write and command line tools.44FairAuth: no auth required

Verdict: choose Agenticorg for coding agents work as a local process; choose Codemcp for coding agents as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Agenticorg logoChoose Agenticorg when

  • You need dedicated capabilities in the Coding Agents domain.
  • You prefer a local stdio subprocess transport.
  • You want tools like list_agents, run_agent, get_agent_details.
Explore Agenticorg

Codemcp logoChoose Codemcp when

  • You need dedicated capabilities in the Coding Agents domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: No auth required.
Explore Codemcp

Feature & specification comparison

Rows where the two servers differ are marked.

SpecAgenticorg logoAgenticorgCodemcp logoCodemcp
CategoryCoding AgentsCoding Agents
Quality signal63/100 · Good44/100 · Fair
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthNot declaredNo auth required
PricingNot declaredFree
Required env varsNone listedNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars131,605
Directory activity 1 views 0 installs 0 upvotes 6 views 0 installs 0 upvotes
Tools16Not listed

Tools & capabilities

Agenticorg tools 16

  • list_agentsList agent records returned by the configured endpoint. Optionally filter by domain.
  • run_agentSubmit a tenant-authenticated, company-scoped request to the configured A2A endpoint.
  • get_agent_detailsGet the agent record returned by the configured endpoint.
  • create_agent_from_sopParse SOP text into a draft configuration that requires review.
  • deploy_agentSubmit a reviewed configuration as a company-scoped shadow candidate.
  • list_connectorsList connector records for discovery. Presence does not establish runtime configuration or execution authority.
  • list_mcp_toolsList agent-tool records returned by the configured MCP endpoint. Results are environment-specific.
  • discover_agents_a2aDiscover available agent skills via A2A (Agent-to-Agent) protocol. Returns agent capabilities, input schemas, and domains.
  • get_agent_cardGet the A2A Agent Card - the public discovery document describing this AgenticOrg instance's capabilities.
  • seller.list_productsList cached Seller Commerce Agent product snapshots with source and freshness metadata.
  • seller.search_productsSearch cached Seller Commerce Agent product snapshots. Results are not transaction authority.
  • seller.get_product_factsAnswer product fact questions from cached Shopify-backed OACP artifacts.
  • +4 more on the listing page

Codemcp tools

No tool names declared yet. Check the project README from the listing page.

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Agenticorg

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "agenticorg": {
      "command": "npx",
      "args": [
        "-y",
        "agenticorg-mcp-server"
      ]
    }
  }
}

Codemcp

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "ezyang-codemcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/ezyang/codemcp@prod",
        "codemcp"
      ]
    }
  }
}

Frequently asked questions

Agenticorg is categorized under Coding Agents and uses a local stdio subprocess. Codemcp belongs to Coding Agents and uses a local stdio subprocess. Pick Agenticorg for coding agents work and Codemcp for coding agents.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Agenticorg has no declared pricing — check the project's own site. Codemcp is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add agenticorg and ezyang-codemcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Agenticorg has a quality signal of 63/100 (Good) with 1 views, 0 installs and 13 GitHub stars. Codemcp has 44/100 (Fair) with 6 views, 0 installs and 1,605 GitHub stars.