MCP server - Can get the tool list, but all tools fail

Hello,

I’m trying to get the MCP server on RT 6.0.4 to work; I’ve been experimenting with a few different agents on my end, from the one that comes with mlx-serve to Lumo Desktop and yes, of course, Claude Code (macOS CLI).

However, even following the exact steps from Jim’s great walk-through video, and the announcement post here, I can’t get any agent to do anything other than confirm that there is an MCP server, and retrieve the list of tools.

Any attempted use of a tool results in a “fetch failed” or other similar (not very useful) error.

I am using a local LLM setup, and have configured Claude Code to point to my OpenAI compatible endpoint and set the appropriate environment variables. This works fine. I can interact with the agent, ask it to analyse code, do things, and everything works as it should.

Checking /mcp also shows RT, and 43 tools.

However, if I actually try to use one, such as from Jim’s video, it fails. Here’s an example:

❯ What user am I logged into RT as?                                                                                                                                                                                                                                                                                                                                                                                                       

∴ The user is asking "What user am I logged into RT as?".
  The available tools include an rt MCP server.
  Specifically, mcp__rt__get_current_user seems like a perfect match for this question.

  First, I need to load the tool schema for mcp__rt__get_current_user. Since it's a deferred tool, I should use ToolSearch to get its definition.

∴ The ToolSearch returned the tool definition. Now I can call it.
  
⏺ rt - get_current_user (MCP)
  ⎿  Error: fetch failed

As you can see, the “fetch failed” isn’t very useful.

I modified my Apache installation for RT to ensure that the SetEnv is present as:

SetEnvIf Authorization "(.*)" HTTP_AUTHORIZATION=$1

Which is set just after the ServerName in the declaration.

I’ve verified the token is correct with a simple curl command, and doing so also updated the “Last Used” timestamp in the RT Web interface for that auth token.

However, whenever I try to use Claude, or any other agent, it seems to get wedged. Eventually things time out, but, it goes in a long loop of arguing with itself about trying to make tool calls, check results, getting empty values, and so on.

I am probably missing something obvious here, but, I’ve verified the .mcp.json file repeatedly in the directory I’m in, know the token is right because I used it with the curl command, and the curl command was also able to do things like get a list of queues over the REST API, but the agent and MCP, nope.

The .mcp.json looks like so:

{
  "mcpServers": {
    "rt": {
      "command": "npx",
      "args": ["mcp-server-rt"],
      "env": {
        "RT_URL": "https://myhost:9009",
        "RT_TOKEN": "1-99-longstuffhere"
      }
    }
  }
}

Yes, I’ve modified it to remove my token. My RT instance runs on a non-standard port, and has a non-globally-trusted TLS certificate. However, I would have assumed if the agent cared about that, it wouldn’t have been able to get the list of 43 tools to start with?

I installed Node.js from homebrew, which is currently v26.13.1, and npx is 11.20.0.

Thank you for any pointers!

That error definitely could be from a trust issue between node and RT. The tool list itself does not require a connection to RT.

You might be missing environment variable NODE_EXTRA_CA_CERTS.

Very helpful, thank you. Setting this to a CRT bundle for my CA and intermediates allowed Claude Code to connect. This is probably my issue with other agents as well, but, they don’t seem to have as easy of a way to work around this.

Unfortunately, Claude is painfully slow, even with the CLAUDE_CODE_ATTRIBUTION_HEADER set to 0. It took 1 minute and 8 seconds for Claude to tell me what user I was logged in to RT as. That hurt.

I was able to use your hint to set some environment variables for Lumo as well - and the local npx command, which worked correctly, and was a LOT faster than Claude, but, I’ll keep trying to get my local LLM to make the connection.