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 agentmods add skills/dribbaengineering/dribba/mcpnpx skills add dribbaengineering/dribba --skill mcpgit clone --depth 1 https://github.com/dribbaengineering/dribbaWhat 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 | $0.00051 | $0.01010 |
| Opus 5 | $0.00026 | $0.00505 |
| Sonnet 5 | $0.00010 | $0.00202 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
mcp scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://dribba.com/mcp \ How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remote MCP server — Dribba
Dribba exposes a remote Model Context Protocol server at
https://dribba.com/mcp (canonical: https://dribba.com/api/mcp). Unlike the
webmcp skill (in-page, browser-only), this is reachable by any MCP client
without loading a page — it's the live case study for the agentic-web work
Dribba sells.
When to use this skill
Use it when the agent should call Dribba by itself: read services, case studies, company facts or a budget range, and — with the user's confirmation — send a contact request. It is the only surface with a write action.
Prefer it over the REST API when you already speak MCP. Prefer rest-api when
you are writing your own HTTP client, and markdown-negotiation when what you
want is the text of a page.
Connect
Add it to an MCP client config:
{
"mcpServers": {
"dribba": { "url": "https://dribba.com/mcp" }
}
}
Or call it directly with JSON-RPC 2.0:
curl -X POST https://dribba.com/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Transport
- MCP Streamable HTTP, stateless JSON mode. POST a JSON-RPC request; the
reply comes back as
application/json(no SSE stream, no session id — every tool is pure request/response). - Protocol version:
2025-06-18. CORS is open (Access-Control-Allow-Origin: *). GETreturns405(no server-initiated stream). Notifications (noid) are acknowledged with202.
Tools (all read-only)
list_services
Dribba's services with one-line summaries and canonical URLs.
get_service
Full summary of one service by slug (e.g. ai-integration, high-performance-engineering).
estimate_project
Ballpark budget (EUR range) mirroring dribba.com's calculator. Params:
platforms (ios/android/web/desktop, required), complexity (mvp/standard/complex),
design (basic/custom/premium), timeline (rush/normal/relaxed). Minimum
project budget is €30,000.
list_projects
Case studies (slug, title, industry).
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.
- yesterday First seen · 114 lines · 51 tokens per session scan A 700d9d810343
mcp is a skill published in the GitHub repository dribbaengineering/dribba (0 stars, last pushed 10d ago), licensed MIT. It adds 51 tokens to every session and 1,010 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
blz-docs-search
Teaches effective documentation search using the blz CLI tool. Use when searching documentation with blz, looking up APIs, finding code examples, retrieving citations, or when questions mention libraries, frameworks, "how to", or documentation topics. Covers BM25 full-text search patterns, citation retrieval, and…
blz-source-management
Teaches how to discover, validate, and add llms.txt documentation sources to the blz CLI. Use when adding documentation to blz, finding llms.txt or llms-full.txt files, validating sources, refreshing content, or managing the documentation index. Covers source discovery, dry-run validation, and index file handling.
web-shaders
Use when writing, debugging, or reviewing shaders for the web — GLSL or WGSL, raw WebGL2/WebGPU, Three.js (ShaderMaterial/RawShaderMaterial/TSL), or React Three Fiber. Covers the language/platform matrix, correct boilerplate, common effects (SDF/raymarching, noise, post-processing), and the pitfalls that make browser…
wiki-ingest
Compile a raw source (document, URL content, meeting notes, research output) into a wikikit agent wiki — merge-don't-overwrite, log contradictions, maintain cross-references, then lint. Use whenever the user says "add this to the wiki", "ingest this", or drops new source material for a wiki maintained with…
claude-archive
Use the Claude Archive — the site for AI — before and after solving any non-trivial problem. Trigger when hitting a bug, error, or tricky task (search/take a scored solution first), and after solving anything reusable (give it back). Also trigger on "check the archive", "archive this", or any mention of the Claude…
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.