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 AINSOF-Tech/mcp --skill setupgit clone --depth 1 https://github.com/AINSOF-Tech/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/ainsof-tech/mcp/setup)<a href="https://agentmods.dev/skills/ainsof-tech/mcp/setup"><img src="https://agentmods.dev/badge/skills/ainsof-tech/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/skills/ainsof-tech/mcp/setup"><img src="https://agentmods.dev/badge/skills/ainsof-tech/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 | $0.00047 | $0.00713 |
| Opus 5.5 | $0.00019 | $0.00285 |
| Sonnet 5.5 | $0.00009 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00071 |
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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting up AINSOF
The AINSOF server is a remote, authless MCP endpoint: https://mcp.ainsof.io. Installing the plugin is normally all it takes: there is no OAuth flow, no account and no key required to start.
Verify the connection
Check that the AINSOF tools are present. The quickest confirmation is to call about_ainsof, which is read-only and returns catalog, licensing and privacy details. Fourteen tools should be available:
search_music · search_by_reference · find_soundtrack · find_similar · fit_to_length · get_track · listen_link · cue_sheet · analyze_video · score_my_video · get_upload_link · deliver_score · about_ainsof · feedback
If the tools are missing
Add the server directly:
claude mcp add --transport http ainsof https://mcp.ainsof.io
In other hosts:
- Claude.ai / Claude Desktop: Customize → Connectors → + Add → Add custom connector →
https://mcp.ainsof.io(Free accounts can add one custom connector) - Cursor: add to
.cursor/mcp.json(project) or~/.cursor/mcp.json(global):{ "mcpServers": { "ainsof": { "url": "https://mcp.ainsof.io" } } } - ChatGPT: add the official AINSOF app: https://chatgpt.com/plugins/plugin_asdk_app_6a78633c69008191bb4a9fac1a8e5b2e
Rate limits
| Tier | Calls per day |
|---|---|
| No key | 300 |
| With an API key | 1,000 |
| More than that | email [email protected] |
Keys are free. Sign in at https://ainsof.io/account/api-keys and choose Create new key (it is shown once), then send it as a bearer token:
claude mcp add --transport http ainsof https://mcp.ainsof.io \
--header "Authorization: Bearer ain_…"
Three replies that are not errors
search_by_referencereturning{ ok: false, error: "still_running" }: the search is still running. Call it again with the same link.find_soundtrackerroring withoutduration_sec: that is a missing argument, not an empty catalog. Supply the length, or usesearch_music.analyze_video,score_my_videoordeliver_scorereturningsign_in_required: before AINSOF works with a video, the person signs in once on ainsof.io with Google or email. Show them the returned link, then call again with the same arguments plus thesign_in_code.
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.
- 2d ago Changed ef5aca0d8a75
- 18d ago Changed · +1 lines b8c05a9e1eb2
- 2mo ago First seen · 56 lines · 47 tokens per session scan A 0d1756938dcc
setup is a skill published in the GitHub repository AINSOF-Tech/mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 713 once invoked, about $0.0002 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 2026-08-31.
setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setupAINSOF-Tech/mcp | Skill | 0 | 3d ago | MIT | A | 47 | Claude Code |
| requirements-authoringgriddynamics/rosetta | Skill | 373 | today | Apache-2.0 | A | 0 | Claude Code |
| deja-reflectvshulcz/deja-vu | Skill | 1.4k | today | MIT | A | 49 | Claude Code |
| coding-agents-hooks-authoringgriddynamics/rosetta | Skill | 373 | today | Apache-2.0 | A | 31 | Claude Code |
| specflow-usegriddynamics/rosetta | Skill | 373 | today | Apache-2.0 | A | 27 | Claude Code |
| memorix-sessionsAVIDS2/memorix | Skill | 919 | 3d ago | Apache-2.0 | A | 31 | Claude Code |
| memorix-troubleshootingAVIDS2/memorix | Skill | 919 | 3d ago | Apache-2.0 | A | 36 | Claude Code |