Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Ask-to-Code write a Python script to calculate fibonacci numbers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An autonomous MCP server that uses the Claude Code CLI to solve coding problems without permission prompts.
# Global install with pipx (recommended)
pipx install git+https://github.com/cjaviersaldana/mcp-ask-to-code.git
# Or with pip
pip install git+https://github.com/cjaviersaldana/mcp-ask-to-code.gitRelated MCP server: codex-cli-mcp-tool
Claude Code CLI installed and authenticated:
npm install -g @anthropic-ai/claude-code# Run (stdio mode for Claude Desktop)
mcp-ask-to-code
# Run with a specific model
mcp-ask-to-code --model claude-sonnet-4-20250514
# Run on a port (SSE mode for multiple sessions)
mcp-ask-to-code --port 8080Argument | Env Variable | Default | Description |
|
| (CLI default) | Model to use (e.g. |
|
|
| Server name |
|
|
| Tool function name |
|
|
| Claude CLI binary path |
|
|
| Port for SSE mode |
|
|
| Host for SSE mode |
Add to your config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/claude-desktop/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"ask-to-code": {
"command": "mcp-ask-to-code",
"args": []
}
}
}{
"mcpServers": {
"ask-to-code": {
"command": "mcp-ask-to-code",
"args": ["--model", "claude-sonnet-4-20250514"]
}
}
}{
"mcpServers": {
"backend-expert": {
"command": "mcp-ask-to-code",
"args": ["--model", "opus", "--name", "Backend Architect"],
"env": {
"MCP_TOOL_NAME": "consult_backend_expert"
}
}
}
}{
"mcpServers": {
"code-agent": {
"command": "mcp-ask-to-code",
"args": ["--model", "claude-sonnet-4-20250514"]
},
"code-reviewer": {
"command": "mcp-ask-to-code",
"args": ["--model", "opus"],
"env": {
"MCP_NAME": "Code Reviewer",
"MCP_TOOL_NAME": "review_code"
}
}
}
}Exposes a single tool (ask_autonomous_agent) to the LLM
Delegates questions to Claude Code CLI with --dangerously-skip-permissions -p
Returns clean output (ANSI codes stripped)
MIT
AUTONOMOUS AGENT: Solves a coding task or answers a question by running an internal agent. This tool has full access to the filesystem, can run tests, read files, and analyze logic.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool has full filesystem access, can run tests, read files, and analyze logic. This alerts the agent to significant capabilities and potential risks, though it does not explicitly mention side effects or destructive actions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no extraneous information. The first sentence states the core function, and the second adds critical behavioral context. Every sentence serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one parameter and an existing output schema, the description adequately covers purpose and behavioral traits. It is missing usage guidelines and parameter elaboration, but given the simplicity, it is mostly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for the single required parameter 'question'. The description provides no additional meaning, format, or constraints beyond the parameter name in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool solves a coding task or answers a question by running an internal agent. It specifies the resource (coding tasks/questions) and action (solving/answering). No siblings exist, so differentiation is not needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for coding tasks and questions but provides no when-to-use or when-not-to-use guidance. While no siblings exist, there is no mention of alternatives or contexts where this tool is unsuitable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.2ask_autonomous_agentOnly one tool exists, so there is no possibility of ambiguity or overlap.
With a single tool, naming is trivially consistent; no pattern conflicts exist.
One tool for a broad coding-assistance domain is extremely thin; typical servers have at least a few tools to separate concerns.
The single tool attempts to cover the entire domain, but users cannot compose or select finer-grained operations, leading to a black-box experience.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server for Grok Imagine AI video generation
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/CJavierSaldana/mcp-ask-to-code'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
