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 karljsamuel/mcp-ecc --skill mcp-eccgit clone --depth 1 https://github.com/karljsamuel/mcp-eccWrote 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/karljsamuel/mcp-ecc/mcp-ecc)<a href="https://agentmods.dev/skills/karljsamuel/mcp-ecc/mcp-ecc"><img src="https://agentmods.dev/badge/skills/karljsamuel/mcp-ecc/mcp-ecc/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/karljsamuel/mcp-ecc/mcp-ecc"><img src="https://agentmods.dev/badge/skills/karljsamuel/mcp-ecc/mcp-ecc.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 | $0.00101 | $0.01218 |
| Opus 5 | $0.00051 | $0.00609 |
| Sonnet 5 | $0.00020 | $0.00244 |
| Haiku 4.5 | $0.00010 | $0.00122 |
Grade A, and why
mcp-ecc 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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-ecc runbook
mcp-ecc is a multi-user MCP server aggregating email, calendar and contacts from Google, Microsoft 365/Outlook, Zoho, IMAP/SMTP, CalDAV and CardDAV. Each user self-manages their own accounts and has their own per-user MCP API key.
Infer provider capabilities
| Provider | Calendar | Contacts | Cloudflare Workers? | |
|---|---|---|---|---|
| ✅ | ✅ | ✅ | ✅ | |
| Microsoft (Graph) | ✅ | ✅ | ✅ | ✅ |
| Zoho | ✅ | ✅ | ✅ | ✅ |
| IMAP / SMTP | ✅ | ❌ | ❌ | ❌ (Node only) |
| CalDAV | ❌ | ✅ | ❌ | ❌ (Node only) |
| CardDAV | ❌ | ❌ | ✅ | ❌ (Node only) |
- Google / Microsoft / Zoho are full-fidelity (mail + calendar + contacts, OAuth).
- IMAP/SMTP is mail only (no calendar/contacts); Microsoft 365 is OAuth-only — app passwords / SMTP basic auth are retired or being retired during 2026.
- CalDAV is calendar only, CardDAV is contacts only (currently scaffolded stubs).
- Cloudflare Workers supports only the HTTP providers (Google, Microsoft, Zoho).
Install & run
Local CLI (stdio — for a desktop agent host)
git clone https://github.com/karljsamuel/mcp-ecc.git
cd mcp-ecc
npm install
npm run build
node packages/cli/dist/bin.js start
Point an MCP host at the stdio command node /abs/path/packages/cli/dist/bin.js start (set MCP_ENCRYPTION_KEY in the host env).
Docker (single container — web UI + REST + MCP on one port 3001)
docker compose up -d # builds + starts; web UI at http://localhost:3001
The /mcp endpoint is Streamable HTTP on the same port: http://<host>:3001/mcp.
First run: bootstrap the admin
Fresh installs have no users. Either use the web UI bootstrap screen, or:
POST /api/auth/bootstrap
{ "username": "admin", "password": "...", "displayName": "Site Admin" }
Only available while the system is empty; this creates the sole admin. Admin endpoints (create/delete users, reset passwords) live under /api/users.
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.
- 8d ago First seen · 91 lines · 101 tokens per session scan A 02231264d174
mcp-ecc is a skill published in the GitHub repository karljsamuel/mcp-ecc (2 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 1,218 once invoked, about $0.0005 per session on Opus 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 2026-09-04.
Other skills, from other repositories
recipe-fullstack-implement
Orchestrate full-cycle implementation across backend and frontend layers.
notion
Notion workspace integration for searching pages, managing databases, creating postmortems, and exporting RCA findings.
news-search
Search current news for a topic, company, competitor, or hook and return dated, attributed articles. Uses the newsjack CLI and Medialyst REST API when available, tries direct Medialyst MCP if the CLI is missing, and falls back to host web/browser search with explicit caveats only when neither cloud path is available.
output-dev-workflow-cost
Calculate and display the cost of an Output SDK workflow execution run. Use when checking LLM token costs, API service costs, or total spend for a specific workflow run.
output-error-direct-io
Fix direct I/O in Output SDK workflow functions. Use when workflow hangs, returns undefined, shows "workflow must be deterministic" errors, or when HTTP/API calls are made directly in workflow code.
auth-security
OAuth 2.1 + JWT authentication security best practices. Use when implementing auth, API authorization, token management. Follows RFC 9700 (2025).