Agent Comms vs Proxyllm MCP

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

Agent Comms logoAgent CommsCommunication · Local subprocess (stdio)Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP49FairAuth: not declaredProxyllm MCP logoProxyllm MCPCommunication · Local subprocess (stdio)OpenAI-compatible LLM gateway: models, savings math, key provisioning, autonomous email-OTP signup56GoodAuth: not declared

Verdict: choose Agent Comms for communication work as a local process; choose Proxyllm MCP for communication as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Agent Comms logoChoose Agent Comms when

  • You need dedicated capabilities in the Communication domain.
  • You prefer a local stdio subprocess transport.
Explore Agent Comms

Proxyllm MCP logoChoose Proxyllm MCP when

  • You need dedicated capabilities in the Communication domain.
  • You prefer a local stdio subprocess transport.
  • You want tools like proxyllm_savings_calculator, proxyllm_list_models, proxyllm_introspect_key.
Explore Proxyllm MCP

Feature & specification comparison

Rows where the two servers differ are marked.

SpecAgent Comms logoAgent CommsProxyllm MCP logoProxyllm MCP
CategoryCommunicationCommunication
Quality signal49/100 · Fair56/100 · Good
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthNot declaredNot declared
PricingNot declaredNot declared
Required env varsNone listedNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars340
Directory activity 1 views 0 installs 0 upvotes 1 views 0 installs 0 upvotes
ToolsNot listed9

Tools & capabilities

Agent Comms tools

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

Proxyllm MCP tools 9

  • proxyllm_savings_calculatorGiven a monthly OpenAI API bill in USD, returns the ChatGPT/Codex subscription tier that absorbs that workload through ProxyLLM Codex Hosted, the flat total (subscription + $129 fee), and the monthly savings. Free, no auth.
  • proxyllm_list_modelsOpenAI-shaped model list from the gateway. No auth required; with a routing key it reflects that key's lanes, including the live Codex catalog.
  • proxyllm_introspect_keyGET /v1/key: the key's provider lanes, reachable models, whether a Codex subscription backs it, and monthly budget state. Authed by the routing key itself.
  • proxyllm_signupStarts autonomous account creation: a 6-digit code is emailed to the operator's inbox (no captcha, no browser). New accounts are unpaid and are removed after 48 hours unless a human activates the membership. Follow with proxyllm_verify_signup.
  • proxyllm_verify_signupExchanges the 6-digit code for an sk_ account token. The token is returned exactly once: store it (PROXYLLM_ACCOUNT_TOKEN). While the account is unpaid the response carries a checkout link to relay to the operator.
  • proxyllm_accountGET /v1/organizations/me. Works while unpaid: plan is "free" plus a payment block until the operator activates the membership, then "pro". Poll this after handing over the checkout link.
  • proxyllm_create_routing_keyMints a pllm_ routing key (returned once) for OPENAI_API_KEY-style use against the gateway. Optionally wires the provider chain in the same call; discover wireable lane ids with proxyllm_list_routing_keys include_lanes.
  • proxyllm_list_routing_keysLists the account's routing keys. include_lanes adds the wireable lanes (connected Codex sessions, bridges, saved provider keys) with the ids provider chains reference.
  • proxyllm_usageGET /v1/organizations/usage for the account.

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.

Agent Comms

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "agent-comms": {
      "command": "npx",
      "args": [
        "-y",
        "agent-comms"
      ]
    }
  }
}

Proxyllm MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "proxyllm-mcp-2": {
      "command": "npx",
      "args": [
        "-y",
        "proxyllm-mcp"
      ]
    }
  }
}

Frequently asked questions

Agent Comms is categorized under Communication and uses a local stdio subprocess. Proxyllm MCP belongs to Communication and uses a local stdio subprocess. Pick Agent Comms for communication work and Proxyllm MCP for communication.

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.

Agent Comms has no declared pricing — check the project's own site. Proxyllm MCP has no declared pricing — check the project's own site. 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 agent-comms and proxyllm-mcp-2 as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Agent Comms has a quality signal of 49/100 (Fair) with 1 views, 0 installs and 34 GitHub stars. Proxyllm MCP has 56/100 (Good) with 1 views, 0 installs and 0 GitHub stars.