Skip to content
Agentmart
Submit a tool

Raptr Agent Builder

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

Connector by kody-w · GitHub account verified by the MCP Registry

IndexedLicense unknownRemote (HTTP)
Write a review

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/kody-w-raptr-agent-builder

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://airaptr-api.azurewebsites.net/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
18 read · 1 write · 0 delete
Secrets
None asked for
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 19

Read from the source code; the running server may list different tools.

Read 18 · Look things up without changing anything.

  • burn_rate
  • check_agent
  • check_domain
  • check_names
  • content_seeds
  • find_agents
  • find_outliers
  • fingerprint_text
  • get_agent_code
  • get_agent_template
  • how_to_run_agent
  • register_domain
Show 6 more tools
  • rejection_rescue_preview
  • setup_checklist
  • share_agent
  • use_agent_here
  • will_it_pass_preview
  • world_now

Write 1 · Create, change, send or run things.

  • request_service

Network hosts it talks to 1

  • airaptr-api.azurewebsites.net · found in remote endpoint, install command

Files it touches

  • Any path the agent passes to its tools

Tools (19)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • burn_rateCheck your monthly burn rateread-only

    Use when someone running a small business or side project lists what they pay each month (servers, software, AI, domains) and wants to know their burn rate. Totals it, compares it with a monthly cap ($100 by default), shows the per-day cost and what running servers fewer hours would save, and names the first thing to cut.

  • check_agentCheck an agent fileread-only

    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.

  • check_domainCheck and price domain namesread-only

    Use when the user wants a domain name, is naming a business or project, or asks whether a domain is taken. Checks up to 20 full domain names (you can suggest variations and check them together) and returns whether each is available and its price.

  • check_namesCheck business namesread-only

    Use when someone is naming a business, startup, product, brand, app, side hustle, shop, podcast or project. Brainstorm candidate names first, then check up to 8 at once: for each, which domains (.com, .co, .ai, .io, .app by default) are free with prices, and whether the GitHub name is free. Results are ranked, a free .com counts most. Suggest new candidates and check again if the best ones are taken.

  • content_seedsTurn your work into content ideasread-only

    Use when someone pastes what they worked on (a list of tasks or commit messages) and wants content from it. Sorts each line into milestones, lessons, numbers, product news and build notes, and says what each kind becomes: shorts, newsletter items, course lessons.

  • find_agentsFind existing agentsread-only

    Searches the open 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.

  • find_outliersFind videos that beat their channelread-only

    Use when someone researching content ideas gives video stats (title, channel subscribers, likes, views). Flags the videos that beat their own channel: more likes than the channel has subscribers, or several times the views. Those are the topics resonating right now.

  • fingerprint_textFingerprint a piece of textread-only

    Use when the user wants to know whether two texts are exactly identical, or wants a fingerprint to compare a document against later. Returns the SHA-256 fingerprint of the exact text, and whether it matches an expected fingerprint if one is given. It does not store the text or prove when it was written.

  • get_agent_codeGet an agent's coderead-only

    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.

  • get_agent_templateGet the agent templateread-only

    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.

  • how_to_run_agentKeep an agent running on your computerread-only

    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.

  • register_domainHow to register a domainread-only

    Use when the user wants to buy an available domain. Explains how to register it: AI agents pay per call; people ask us and we register it for them. Nothing is bought by this tool.

  • rejection_rescue_previewExplain an App Store rejectionread-only

    Use when the user pastes a rejection message from Apple App Review (it cites guidelines such as "Guideline 5.1.1(i)"). Free. Returns each cited guideline section it recognizes, with its title and what Apple means by it, and lists sections it does not know. The full version (likely causes, a fix list and a reply draft to App Review) is a separate paid HTTP call; the result says its price and route.

  • request_serviceAsk us to build something

    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.

  • setup_checklistAI business stack checklistread-only

    Use when someone is setting up a small online business (YouTube channel, newsletter, store) and wants to know what's next. Pass the steps already done; returns what's left, in order, with time estimates.

Show 4 more tools
  • share_agentShare an agent with everyoneread-only

    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 open agent registry under their own GitHub account. Nothing is published by this tool.

  • use_agent_hereUse the agent in this chatread-only

    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.

  • will_it_pass_previewCheck an App Store listing before submittingread-only

    Use before submitting an app to the App Store, when the user has the listing (name, subtitle, keywords, description, copyright, privacy and support URLs; optionally screenshots, review notes, Info.plist keys). Free. Runs the checks a machine can run against the reasons Apple rejects listings (Apple product names, other companies' names, length limits, placeholders, screenshot sizes, public privacy and support pages...) and says PASS, FAIL, WARN or NOT_CHECKED per check, plus what only a person can confirm. What was found and the fix for each failure is a separate paid HTTP call; the result say…

  • world_nowVerified snapshot of the world right nowread-only

    Use when the user asks what is happening in the world right now and wants numbers they can trust and cite: Bitcoin and crypto market, currency exchange rates, earthquakes in the past hour, space weather, where the International Space Station is, and more. Every snapshot carries its public tick number, time and SHA-256 fingerprint so anyone can check it later.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Oct 16, 2026 (12 days ago)
Last release
Oct 5, 2026 (23 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.kody-w/raptr-agent-builder
Version
1.0.0
Auth
Auth not stated
License
License unknown
Repository
github.com/kody-w/airaptr
Website
kody-w.github.io/airaptr/
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from kody-w

Cite this page

Raptr Agent Builder MCP server. Agent Mart. https://agentmart.dev/connectors/kody-w-raptr-agent-builder (last updated 2026-10-24)