Skip to main content
Glama
moliver28

anythingllm-mcp

by moliver28

chat

Send a chat message to a workspace in chat or query mode to interact with AI-powered document chat and retrieve answers.

Instructions

Send a chat message to a workspace (mode: chat or query)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workspaceYes
messageYes
modeNo
userIdNo

Implementation Reference

  • Handler logic for both chat_send and chat_stream tools. Sends POST to AnythingLLM API with workspace and message.
    else if (name === "chat_send") { result = await apiRequest("/workspace/" + args?.workspace + "/chat", "POST", { message: args?.message }); }
    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 }); }
  • Input schema definitions for chat_send and chat_stream tools, requiring workspace and message string properties.
    { name: "chat_send", description: "Send chat message", inputSchema: { type: "object", properties: { workspace: { type: "string" }, message: { type: "string" } }, required: ["workspace", "message"] } },
    { name: "chat_stream", description: "Stream chat", inputSchema: { type: "object", properties: { workspace: { type: "string" }, message: { type: "string" } }, required: ["workspace", "message"] } },
  • src/index.ts:64-82 (registration)
    Registration of all tools including chat_send and chat_stream via ListToolsRequestSchema handler.
        tools: [
          { name: "auth_verify", description: "Verify API token", inputSchema: { type: "object", properties: {}, required: [] } },
          { name: "system_check_token", description: "Check API token", inputSchema: { type: "object", properties: {}, required: [] } },
          { name: "system_generate_api_key", description: "Generate API key", inputSchema: { type: "object", properties: {}, required: [] } },
          { name: "system_env_dump", description: "Get system environment", inputSchema: { type: "object", properties: {}, required: [] } },
          { name: "workspace_list", description: "List all workspaces", inputSchema: { type: "object", properties: {}, required: [] } },
          { name: "workspace_get", description: "Get workspace details", inputSchema: { type: "object", properties: { slug: { type: "string" } }, required: ["slug"] } },
          { name: "workspace_create", description: "Create workspace", inputSchema: { type: "object", properties: { name: { type: "string" }, slug: { type: "string" } }, required: ["name"] } },
          { name: "workspace_update", description: "Update workspace", inputSchema: { type: "object", properties: { slug: { type: "string" }, name: { type: "string" } }, required: ["slug"] } },
          { name: "workspace_delete", description: "Delete workspace", inputSchema: { type: "object", properties: { slug: { type: "string" } }, required: ["slug"] } },
          { name: "chat_send", description: "Send chat message", inputSchema: { type: "object", properties: { workspace: { type: "string" }, message: { type: "string" } }, required: ["workspace", "message"] } },
          { name: "chat_stream", description: "Stream chat", inputSchema: { type: "object", properties: { workspace: { type: "string" }, message: { type: "string" } }, required: ["workspace", "message"] } },
          { name: "thread_list", description: "List threads", inputSchema: { type: "object", properties: { workspace: { type: "string" } }, required: ["workspace"] } },
          { name: "document_list", description: "List documents", inputSchema: { type: "object", properties: {}, required: [] } },
          { name: "openai_list_models", description: "List models", inputSchema: { type: "object", properties: {}, required: [] } },
          { name: "openai_chat_completion", description: "Chat completion", inputSchema: { type: "object", properties: { model: { type: "string" }, messages: { type: "array" } }, required: ["model", "messages"] } },
        ],
      };
    });
  • Generic HTTP request helper used by all tool handlers including chat_send and chat_stream to make API calls.
    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 provided; description only states action without disclosing side effects, authentication needs, or return behavior. For a message-sending tool, critical details like response or error handling are missing.

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?

Single sentence is concise but lacks necessary details. It is front-loaded but incomplete, sacrificing completeness for brevity.

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

Completeness2/5

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

With no output schema, no annotations, and 4 parameters, the description is insufficient. It fails to explain return values, error conditions, or mode semantics, leaving agents underinformed.

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 coverage is 0% and description only mentions 'mode' enum. No explanation for workspace, message, or userId beyond their existence. The description adds minimal value over schema.

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?

Description clearly states the tool sends a chat message to a workspace, with modes 'chat' or 'query'. It specifies a verb and resource, but does not differentiate from sibling tools like 'openai_chat_completion' or 'stream_chat'.

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 on when to use this tool versus alternatives. Lacks context on appropriate mode selection or prerequisites.

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