Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add george-kozlitin/borme-mcp --skill borme-registrygit clone --depth 1 https://github.com/george-kozlitin/borme-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/george-kozlitin/borme-mcp/borme-registry)<a href="https://agentmods.dev/skills/george-kozlitin/borme-mcp/borme-registry"><img src="https://agentmods.dev/badge/skills/george-kozlitin/borme-mcp/borme-registry/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/george-kozlitin/borme-mcp/borme-registry"><img src="https://agentmods.dev/badge/skills/george-kozlitin/borme-mcp/borme-registry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00178 | $0.02258 |
| Opus 5.5 | $0.00071 | $0.00903 |
| Sonnet 5.5 | $0.00036 | $0.00452 |
| Haiku 4.5 | $0.00018 | $0.00226 |
Grade A, and why
borme-registry scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BORME — the gazette of Spain's commercial registry
The borme MCP server holds the company notices of BORME Section A since
2009, parsed into typed events, plus tax-ID and trademark lookups. This
skill says which tool to call, how to chain them, and how to report what comes
back. Each tool's description and parameter schema explain its parameters;
read them too.
Connect
The hosted endpoint is https://mcp.bormeapi.com/mcp (Streamable HTTP). It
works without a key on the free plan. With a key, send it in the X-API-Key
header:
- Claude Code:
claude mcp add --transport http borme https://mcp.bormeapi.com/mcp --header "X-API-Key: YOUR_KEY" - Clients configured with JSON (Cursor's
mcp.jsonand similar):{"mcpServers": {"borme": {"url": "https://mcp.bormeapi.com/mcp", "headers": {"X-API-Key": "YOUR_KEY"}}}}
Keys: https://bormeapi.com/account. Plans and prices: https://bormeapi.com/pricing.
If the borme tools are not available in this session, say the BORME MCP
server is not connected, give the user the lines above, and do not answer from
memory.
What each plan includes
- No key (free):
search_events,company_historyanddaily_digestover the last 7 days;list_act_typesandregistry_stats. 50 calls a day per IP address. - basic: the last 365 days, plus
company_by_nif,brand_ownerandcompany_brands. - pro: everything in basic, with the full history back to 2009.
- risk: everything in pro, plus
recent_signals.
When an answer carries plan_window, the plan's window was applied
(company_history carries it on every free or basic answer). Tell the user
once, in one sentence, and say what covers the rest: a key for the last 365
days (basic), pro for the full history. Do not retry with older dates — the
server cuts them the same way — and do not take an empty result as proof that
nothing happened earlier.
A refusal that names a plan, or says a company's notices lie outside the window, is not a server failure: relay its message, say which plan covers it, and do not retry.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 20d ago First seen · 157 lines · 178 tokens per session scan A 692b660387c8
borme-registry is a skill published in the GitHub repository george-kozlitin/borme-mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 178 tokens to every session and 2,258 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.
borme-registry compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| borme-registrygeorge-kozlitin/borme-mcp | Skill | 0 | 20d ago | MIT | A | 178 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 2d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 2d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | yesterday | MIT | A | 49 | Claude Code |
| regulatory-research-fallbackHKUDS/OpenSpace | Skill | 7.9k | 2d ago | MIT | A | 20 | Claude Code, Codex |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 9d ago | Apache-2.0 | A | 57 | Claude Code, Codex |