Llmconveyors MCP Server

MCP server that connects AI agents to LLM Conveyors — run Job Hunter, B2B Sales, and other AI agents from Claude, Cursor, or any MCP client. The llmconveyors mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

A community-driven AI agent platform with pay-per-action pricing ($1–5 per completed action). Instead of $100/mo SaaS subscriptions, you pay only for real outputs — a resume scored, a company researched, a cold email generated.

Adding it to your client

llmconveyors-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Its toolset

Everything the assistant can do here goes through one of these:

• settings-profile — Get user profile (credits, plan)
• settings-preferences-get — Get user preferences
• settings-preferences-update — Update user preferences
• settings-usage-summary — Get usage summary
• settings-usage-logs — Get paginated usage logs
• api-key-create — Create a new API key
• api-key-list — List all API keys
• api-key-revoke — Revoke an API key
• api-key-rotate — Rotate an API key
• api-key-usage — Get usage statistics for a specific API key
• byo-key-get — Check if a Bring Your Own API key is configured
• byo-key-set — Set a BYO API key for a provider (e.g. Gemini)

Configuration

You will need 2 environment variables: LLMC_API_KEY, LLMC_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

• Node.js >= 18 - An LLM Conveyors API key (get one here)

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Llmconveyors MCP.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the llmconveyors mcp mcp server does with a few real requests.

When to reach for it

This sits in the monitoring and observability group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Llmconveyors MCP's toolset — settings-profile, settings-preferences-get, settings-preferences-update and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ebenezer-isaac; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.