Skip to main content
Glama
Sign In

rapp-agent-builder

by io.github.kody-w
OverviewDiscussionsAdmin

Server Details

Turn an idea or meeting transcript into a working single-file AI agent, check it, use it right away.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
Repository
kody-w/rapp-chatgpt
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A4.1/5.0

Scored across 8 tools

Disambiguation4/5

Each tool targets a distinct step in the agent lifecycle: discovery (find_agents), fetching code (get_agent_code), templating (get_agent_template), validation (check_agent), running (use_agent_here/how_to_run_agent), and sharing (share_agent). Minor overlap exists since share_agent also 'checks' an agent (overlapping with check_agent) and both use_agent_here and share_agent are described as follow-ups to check_agent, but the descriptions distinguish them well.

Naming Consistency4/5

Almost all names follow a clean snake_case verb_noun pattern (check_agent, find_agents, get_agent_code, share_agent). how_to_run_agent deviates from the verb_noun convention, but it remains snake_case and readable, so the set is largely predictable.

Tool Count5/5

Eight tools is well-scoped for an agent-builder workflow. Each tool earns its place across discovery, templating, validation, running, and sharing, with no redundant entries.

Completeness4/5

The surface covers the full lifecycle: find existing agents, fetch code, get a template, validate, run in-chat, run locally, share, and a request_service fallback for out-of-scope needs. The only mild gap is no explicit tool for editing/updating an existing agent file beyond rewriting and re-checking.

Available Tools

8 tools
check_agentCheck an agent fileA
Read-only
Inspect

Checks a finished agent file against the template rules (manifest, naming, class, perform method, no hardcoded secrets). Call it on every agent you write, fix anything it reports, and call it again until it passes.

Inputs: code (required), filename (required).

find_agentsFind existing agentsA
Read-only
Inspect

Searches the public agent registry (about 1,700 single-file agents) for agents that already do what the user wants, for example when they ask 'is there an AI tool for...' or want a ready-made automation instead of building one. Use it before building from scratch, or when the user asks whether an agent exists for a task.

Inputs: query (required), limit.

get_agent_codeGet an agent's codeA
Read-only
Inspect

Returns the full source of one agent from the registry, by its name (e.g. @bill/neuron_agent), so it can be read or adapted.

Inputs: name (required).

get_agent_templateGet the agent templateA
Read-only
Inspect

Use this when the user wants to build an AI agent, assistant, bot or automation from an idea, a repetitive task, a process description, or a meeting transcript (for example: automate invoices, triage support tickets, summarize meetings, follow up with leads). Returns the official single-file agent template and its rules. Fill it in yourself from what the user described, then call check_agent on the finished file before showing it to the user. Then call use_agent_here so the user can use it right away in this chat.

Inputs: no named parameters.

how_to_run_agentKeep an agent running on your computerA
Read-only
Inspect

Optional, for later: how to keep an agent running on the user's own computer with the free Brainstem. Only offer this after the user has used the agent in the chat and wants to keep it.

Inputs: os, filename.

request_serviceAsk us to build somethingAInspect

Use when the person wants something none of these tools can do and says yes to passing the request on. Records only the request text they agree to send (no name or contact). Ask before calling it.

Inputs: request (required).

share_agentShare an agent with everyoneA
Read-only
Inspect

Use only when the user says they want to share an agent they built. Checks the agent and scans it for personal details (emails, phone numbers, secrets), then explains how to publish it to the free public agent registry under their own GitHub account. Nothing is published by this tool.

Inputs: code (required), filename (required).

use_agent_hereUse the agent in this chatA
Read-only
Inspect

Use this right after an agent passes check_agent, or whenever the user wants to try an agent. Returns a short Python runner so you can run the agent in this chat with your own Python tool on the user's own data (pasted text, an uploaded spreadsheet, a list). Nothing to install. If Python is unavailable, apply the agent's logic yourself by reading its code. Ask the user for their real data, run the agent, and show the result in plain words.

Inputs: filename.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • keelyard

      akobirjontulqinovfuture
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables users to make AI coding agents prove their work with passing tests before finishing, snapshot every edit so any step can be undone, and trim noisy tool output to save tokens. Runs locally with no telemetry and works with Claude Code, Codex and OpenCode.
      111 PyPI
      4
      Apache 2.0

    • Glassbox

      DERYK-RYLOY
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI coding agents to turn plans into structured artifacts that are recursively verified, scored 0–100 for trust with a plain-English verdict, and documented with receipts and renderable reports. It also provides a recursive multi-agent deep-thinking pipeline and an in-process Tiny Thinker for relevance gating and deduplication.
      1
      MIT
    Try in Browser
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources