Skip to main content
Glama
moliver28

anythingllm-mcp

by moliver28

stream_chat

Stream a chat message to a workspace and receive a real-time response, supporting modes like chat and query for interactive conversations.

Instructions

Stream a chat message to a workspace

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workspaceYes
messageYes
modeNo
userIdNo
threadSlugNo

Implementation Reference

  • Handler for the chat_stream tool - calls the /workspace/{workspace}/stream-chat API endpoint with POST method, passing the user's message as the body.
    else if (name === "chat_stream") { result = await apiRequest("/workspace/" + args?.workspace + "/stream-chat", "POST", { message: args?.message }); }
    else if (name === "thread_list") { result = await apiRequest("/workspace/" + args?.workspace); result = { threads: result?.workspace?.threads || [] }; }
    else if (name === "document_list") { result = await apiRequest("/documents"); }
    else if (name === "openai_list_models") { result = await apiRequest("/openai/models"); }
    else if (name === "openai_chat_completion") { result = await apiRequest("/openai/chat/completions", "POST", { model: args?.model, messages: args?.messages }); }
    else { throw new McpError(ErrorCode.MethodNotFound, "Unknown tool: " + name); }
  • src/index.ts:75-75 (registration)
    Registration of the chat_stream tool in the ListToolsRequestSchema handler, defining its name, description ("Stream chat"), and input schema requiring workspace and message strings.
    { name: "chat_stream", description: "Stream chat", inputSchema: { type: "object", properties: { workspace: { type: "string" }, message: { type: "string" } }, required: ["workspace", "message"] } },
  • Helper function apiRequest that handles HTTP/HTTPS requests to the AnythingLLM API, used by chat_stream to make the POST request.
    function apiRequest(path: string, method = "GET", body?: any, extraHeaders = {}): Promise<any> {
      return new Promise((resolve, reject) => {
        const baseUrl = new URL(ANYTHING_LLM_BASE);
        const fullUrl = new URL(path, baseUrl);
        const options: any = {
          hostname: fullUrl.hostname,
          port: fullUrl.port || (fullUrl.protocol === "https:" ? 443 : 80),
          path: fullUrl.pathname + fullUrl.search,
          method,
          headers: Object.assign({
            "Authorization": "Bearer " + ANYTHING_LLM_API_KEY,
            "Content-Type": "application/json",
            "Accept": "application/json",
          }, extraHeaders),
        };
    
        const lib = fullUrl.protocol === "https:" ? https : http;
        const req = lib.request(options, (res: any) => {
          let data = "";
          res.on("data", (chunk: string) => { data += chunk; });
          res.on("end", () => {
            try {
              resolve(data ? JSON.parse(data) : {});
            } catch {
              resolve({ raw: data });
            }
          });
        });
        req.on("error", reject);
        if (body) req.write(JSON.stringify(body));
        req.end();
      });
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It does not disclose behavioral traits such as streaming behavior, rate limits, or authentication requirements. The description is too brief to be informative.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words. However, it is under-specified for a tool with five parameters, making it less effective despite its brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (5 parameters, streaming behavior, no output schema or annotations), the description is extremely incomplete. It does not explain the return format, streaming mechanics, or parameter purposes, leaving major gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, requiring the description to add meaning beyond the schema. However, the description provides no parameter semantics, leaving five parameters (including one with an enum) unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Stream a chat message to a workspace' clearly states the verb and resource. However, it does not differentiate from sibling tools like 'chat' or 'openai_chat_completion', which may have similar functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'chat' or 'openai_chat_completion'. There are no exclusions or context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/moliver28/anythingllm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server