Skip to main content
Glama

BOTERNITY · free remote MCP server for AI agents

MCP score BOTERNITY MCP connector MCP Registry

BOTERNITY gives AI agents what they cannot do alone: read any web page cleanly, watch pages for changes over days, audit MCP servers, transform data and keep notes across sessions.

  • No account, no API key, free (fair-use quotas; optional access keys for more).

  • Deterministic: no model behind it, nothing you send is executed.

  • Every door: MCP (Streamable HTTP), REST with OpenAPI 3.1, A2A agent card, llms.txt.

  • Safe by design: every tool carries MCP annotations (readOnlyHint, destructiveHint), so clients know which ones only read.

This repository holds the public documentation and metadata. The server is hosted: there is nothing to install.

https://boternity.com/api/public/v4/mcp

Connect

Claude Code

claude mcp add --transport http boternity https://boternity.com/api/public/v4/mcp

Claude (claude.ai and desktop app): Settings → Connectors → Add custom connector, then paste the URL above.

Cursor (~/.cursor/mcp.json)

{"mcpServers": {"boternity": {"url": "https://boternity.com/api/public/v4/mcp"}}}

VS Code (.vscode/mcp.json)

{"servers": {"boternity": {"type": "http", "url": "https://boternity.com/api/public/v4/mcp"}}}

ChatGPT custom GPT actions and API clients: import https://boternity.com/api/public/v4/openapi.json.

Plain HTTP

curl -X POST https://boternity.com/api/public/v4/tools/read_page \
  -H "Content-Type: application/json" -d '{"url": "https://example.com"}'

A2A (Agent2Agent): agent card at https://boternity.com/.well-known/agent-card.json, JSON-RPC endpoint https://boternity.com/api/public/v4/a2a (message/send with a data part {"skill": "read_page", "arguments": {...}}).

Related MCP server: Finch MCP

Tools (29)

Area

Tools

What it does

Web pages

read_page

Clean text (headings as Markdown), title, description, language, canonical URL, Open Graph, schema.org types, outline, links. robots.txt respected, 10-minute cache, pagination.

Page watching

watch_page, get_watch, check_watch_now, stop_watch

Re-reads a page on a schedule and keeps diffs, changed sections and keyword events. Watch only part of a page (CSS selector), get a webhook POST on change.

MCP audit

test_mcp_server, get_mcp_test

Scores a remote MCP server out of 100: initialize, version negotiation, sessions, tools/list schema lint and token cost, ping, error codes, resources, prompts, CORS, Origin, latency, optional real tool call. JSON and Markdown report.

Memory

create_notebook, write_note, read_notes, delete_note

A private notebook per agent (secret token) that survives across sessions, for 30 days after last use.

Data

convert_data, inspect_json, analyze_table, compare_tables, clean_table, compare_texts

JSON ⇄ CSV ⇄ XML, validation and RFC 6901 pointers, per-column statistics, table comparison by key, cleaning, text diffs.

Time

get_current_time, convert_time, compute_duration, list_cron_runs

Present moment, IANA timezones with daylight saving time, durations, next cron runs.

Utilities

encode_text, generate_uuid, parse_url, explain_http_status

Base64 and URL encoding, hashes, UUIDs, URL parsing, HTTP status codes with retry guidance.

Catalog

search_catalog, read_catalog_resource, request_resource, get_request_status

Verified extracts of specifications (MCP, HTTP, OpenAPI, robots.txt); ask for what you need.

Names from versions 1.x (current_time, json_to_csv, data_stats, note_put…) still work.

The server also exposes MCP prompts (audit_mcp_server, watch_price, summarize_page, track_document_changes, compare_tables, remember_across_sessions) and resources (catalog extracts, boternity://watch/{id}, boternity://mcp-test/{id}).

Try it

Ask your agent, once connected:

  • Use BOTERNITY to read https://www.rfc-editor.org/rfc/rfc9110.html and summarize it.

  • With BOTERNITY, watch the price block of this product page every 6 hours and track "out of stock".

  • Audit my MCP server https://example.com/mcp with BOTERNITY and give me the three most important fixes.

  • Create a BOTERNITY notebook for this project and save our decisions there after each session.

More on boternity.com/examples. Audit your own MCP server for free at boternity.com/mcp-audit and add your score badge to your README.

Security and privacy

  • Inputs are not stored, except a watched page's text, a notebook's notes and an MCP audit report, all temporary. Do not send personal data. Full details: privacy policy.

  • Outgoing requests (page reading, watching, audits) run in an isolated worker that cannot reach private or local networks; every redirect is re-checked.

  • No cookies, no tracking of individual users; client IP addresses are not stored by the gateway.

Support

Open an issue · support page · terms

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

    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Portable MCP memory server giving AI agents persistent, verified, cross-session memory. 30 tools, SQLite + cloud sync, Chrome Extension for every AI chat platform. The only JavaScript MCP memory server. Includes behavioral learning engine, semantic search, knowledge scoping, session quality scoring, and web dashboard.
      -
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI assistants to retain persistent, searchable memory and versioned vaults, spawn and recall named agents with state and audit history, run automations, monitors, and deep research, and execute on-chain and web tasks across sessions. It can be installed alongside Claude Code, Cursor, Windsurf, Zed, Hermes, and other MCP clients, with vault and memory optionally run entirely on the user's machine.
      45
      235 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to drive a real Chrome instance over the Chrome DevTools Protocol — opening and navigating tabs, reading compact YAML page outlines with refs, clicking, typing, scrolling, screenshotting, and evaluating scripts — with no browser extension or installed dependencies. It also audits pages for horizontal overflow and WCAG AA contrast, available both as an MCP tool and as a CI-friendly CLI.
      15 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to register an identity and API key, call free tools such as prop-firm drawdown rules, an AI-writing check, and current LLM per-token pricing, and keep versioned memory, notes, and end-to-end encrypted storage that persists across restarts. It also lets agents claim and verify jobs, publish profiles and skills with A2A/MCP/x402 endpoints, and discover other agents by skill or tag.
      MIT