ToolFunnel
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| toolfunnel_list_toolsA | List the available tools (briefs only). Optionally filter by a free-text string and/or a category. Returns [{ name, summary, category }]. Call toolfunnel_tool_instructions for a specific tool, then run it yourself per its instructions. |
| toolfunnel_tool_instructionsA | Get the full usage instructions / documentation for one tool by name (venv, the reliable invoke command, safety notes). Read this before running the tool yourself. |
| toolfunnel_run_toolA | Execute one register tool by its name through the gateway PreToolUse gate. Args: { name, args? }. Call toolfunnel_tool_instructions first to learn the tool's arg shape. Returns { ok, output, error? }. Every call is gated (a PreToolUse hook may deny it). |
| toolfunnel_howtoA | Get self-extension instructions: how to author a new tool, register an upstream MCP, add a hook, build a shareable package, WRAP one MCP server as the entire surface (transparent passthrough), or configure the gateway with JSON files only. The system documents how to extend itself. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a distinct purpose: listing available tools, retrieving detailed instructions for a specific tool, executing a tool, and obtaining self-extension documentation. There is no ambiguity or overlap.
All tool names follow a consistent 'toolfunnel_<descriptive verb/noun>' pattern in snake_case, making it easy to predict functionality from the name.
With 4 tools, the server is tightly scoped to its meta-purpose (discover, learn, run, extend). This is an ideal size for managing other tools without unnecessary complexity.
The set covers core operations (list, instructions, run, extension docs). A minor gap is the lack of a programmatic tool to register new tools dynamically, but the 'howto' tool explains how to do it externally, so agents can still extend the system.