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.
git clone --depth 1 https://github.com/unblockingapi/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/commands/unblockingapi/mcp/setup)<a href="https://agentmods.dev/commands/unblockingapi/mcp/setup"><img src="https://agentmods.dev/badge/commands/unblockingapi/mcp/setup/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/commands/unblockingapi/mcp/setup"><img src="https://agentmods.dev/badge/commands/unblockingapi/mcp/setup.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 | $0.00012 | $0.00480 |
| Opus 5.5 | $0.00005 | $0.00192 |
| Sonnet 5.5 | $0.00002 | $0.00096 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
setup 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 3d 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.
What it actually says
Walk the user through getting UnblockingAPI working. Be brief and concrete — they may never have set up an MCP server before. Do not dump all the steps at once; diagnose first, then give them only the step they actually need.
1. Find out where they stand
Call unblock_fetch with url: "https://example.com". One of these happens:
- It succeeds → they are done. Tell them so, mention that each successful fetch costs 1 credit and failures are free, and show them one thing they can now ask for (see step 3).
- The tool is missing, or it says sign-in is required → go to step 2.
- It says out of credits (HTTP 402) → the setup is fine; they need to top up at https://unblockingapi.com/billing.
2. Sign in
The plugin connects to the hosted server at https://mcp.unblockingapi.com/mcp, which signs in with their UnblockingAPI account. There is no key to copy.
Tell them to run /mcp, pick unblockingapi and choose Authenticate. A
browser opens on app.unblockingapi.com: they sign in (or sign up — new accounts
get 500 free credits with no card) and approve the connection.
Then run unblock_fetch on https://example.com again to confirm, and say plainly
whether it worked. If sign-in keeps failing, they can clear it from /mcp and
authenticate again.
3. Show them what it is for
Once it works, give them one or two concrete things to try, chosen for what they seem to care about — not a feature list:
- Reading a page that needs JavaScript or refuses simple requests, with
unblock_fetch. - Structured JSON instead of HTML: call
find_templateswith a site they care about, and if a template covers it, fetch withtemplate:set. - A page from another country, with
location: "de"or similar.
Mention that they can build a template for any site at https://editor.unblockingapi.com.
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.
- 3d ago Changed · -17 lines · -4 tokens per session c6d768f3fb8d
- 1mo ago First seen · 63 lines · 16 tokens per session scan A 8232d18d272c
setup is a command published in the GitHub repository unblockingapi/mcp (2 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 480 once invoked, about $0.0000 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 2026-09-10.
Other commands, from other repositories
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
intercept
HTTP sniffer for tandem's Chrome via CDP, all tabs: captures request+response bodies (private APIs, CSRF tokens). Subcommands: start (background), stop, status, show, clear, count.
playbook
Manage Mochi playbooks (list, show, run, delete). Plays through the browser MCP tools.
t00-playwright-test
A command for testing a locally running web app in a real browser with Playwright, a browser automation and testing tool. It checks normal user flows and selected edge cases, then reports results with screenshots.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.