Have an AI agent? Let it explore Baltor for you. Any assistant works, personal or coding.

Connect your agent
What your agent reads

The request it copies

Explore baltor.ai for me and report back. Start with https://baltor.ai/llms.txt, then read https://baltor.ai/.well-known/agent-card.json and https://baltor.ai/.well-known/mcp.json. Tell me which plan (Feeds at $4.99/mo, Pro at $29/mo, or Max at $49/mo) fits my work, what you would connect, and the setup steps at https://baltor.ai/connect. Stay read-only: read public pages and agent files, and check with me before any sign-in, purchase or change. If a step needs a key, name it (BALTOR_SERVICE_TOKEN) and I will add it myself.

Discovery files on baltor.ai

Read-only discovery is open. Keep BALTOR_SERVICE_TOKEN in your own environment.

Baltor
Sign in
Baltor

Get started with Baltor

Create your account, choose a plan and connect the agent you already use. About five minutes.

Step 1 of 6

Create your account

Start with just your email address. We send you a link to confirm it, then you choose a password.

By creating an account you agree to the terms of service and the privacy notice.

Already have an account? Sign in

Creating an account keeps your plan choice open. You choose Feeds, Pro or Max in step 4.

Step 2 of 6

Check your inbox

Open the link we sent to {{ email }}. It confirms your address and opens the page where you choose your password.

From
accounts@mail.baltor.ai
To
{{ email }}
Subject
Confirm your Baltor account

Waiting for you to open the link

Sent again. The newest link is the one that works.

In this preview, Open the link stands in for the button in the email.

Step 3 of 6

Choose a password

{{ email }} is confirmed.

You sign in with your email address and this password.

{{ pw.text }}

{{ pw2.text }}

Step 4 of 6

Choose a plan

You are signed in as {{ email }}. Pick the plan that fits the work.

Plan
  • Card details stay with Stripe.
  • Your access turns on once Baltor confirms the subscription.
  • Cancel any time from your account page.
Compare the plans

Step 5 of 6

Connect your agent

Checkout complete. {{ planName }} is active on your account.

Feeds is active on your account, free through December 31, 2026 (Eastern).

Pick the agent you use: Claude Code, Codex, OpenCode, Pi (an open-source terminal coding agent) or Baltor’s own agent. Give it a key and one configuration entry.

  1. Choose your agent

    Claude Code reads skills from .claude/skills/.Open the Claude Code guide
    Codex reads skills from .agents/skills/.Open the Codex guide
    OpenCode reads skills from .opencode/skills/.Open the OpenCode guide
    Pi reads skills from .pi/skills/.Open the Pi guide
    The Baltor Harness reads the task file it is given.Open the Baltor Harness guide

    17 more connect over MCP, including Cursor, Gemini CLI, GitHub Copilot, Windsurf and Zed.

  2. Create a key

    One key for each tool or device. It can search and download what your plan allows.

    We show each key once. Keep it in your environment as BALTOR_SERVICE_TOKEN.

  3. Keep it in your environment and add one entry

    Bash
    read -rsp "Baltor service token: " BALTOR_SERVICE_TOKEN
    export BALTOR_SERVICE_TOKEN
    # When you are done
    unset BALTOR_SERVICE_TOKEN
    Entry JSON
    { "mcpServers": { "baltor": {
    "type": "http",
    "url": "https://baltor.ai/mcp",
    "headers": {
    "Authorization": "Bearer ${BALTOR_SERVICE_TOKEN}"
    }
    } } }

    Merge the entry into your existing configuration. It holds the variable name; your key stays in your environment.

  4. Test the connection

    It checks metadata only and lists the tools your connection can use. ConnectedTools:intelligence_searchprovisioning_manifestprovisioning_readpublic_good_files

Step 6 of 6

Make your first download

Ask your agent for a real task. It searches first, checks the result and downloads the exact version it chose.

Ask your agent

Search Baltor for a skill that turns an OpenAPI spec into an MCP server. Show its source, licence and requirements before downloading it.

{{ harnessSlug }}
1. Search
intelligence_search "MCP server from an OpenAPI spec"
openapi-to-mcp-serverskill, MIT, 6.4 KB, sha256 3f9c1a07…
mcp-tool-schema-checkscode module, Apache-2.0, 2.2 KB, sha256 b81e44d2…
2. Download the exact version
provisioning_read
identity openapi-to-mcp-server
expected_digest 3f9c1a07…
Checksum matches
3. Place it
{{ placeLine }}
  • Your harness decides what runs, with the permissions you choose.
  • One item at the version you selected counts once. Searches, second looks at the same reference and refused downloads are free.