spytrend-mcp
llms.txt30 starsChanged 3 months agoMITView on GitHub
Spytrend is an advertising analytics platform. It covers advertising from Meta and TikTok and lets you see not one placement at a time but everything a single account runs — every ad, video, page, domain, country and run date at once. It connects to AI assistants over the Model Context Protocol. One ad is a single frame. This shows the whole body of work. Endpoint: https://mcp.spytrend.com/mcp — Streamable HTTP, browser sign-in with a Spytrend account. Nothing to install, no key…
In this repository6 other files it gives its agents.
The file
We split this llms.txt into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 31
Search: search_ads, search_creatives, search_advertisers, search_webmasters, search_hubs, search_shops
- Very specific: line 35
Look-alikes: find_similar_ads, find_similar_creatives, find_similar_webmasters, get_webmaster_similarity_facets
≈ “Common” is an estimate: at least 1 in 5 of the 3,727 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# Spytrend > Spytrend is an advertising analytics platform. It covers advertising from Meta > and TikTok and lets you see not one placement at a time but everything a single > account runs — every ad, video, page, domain, country and run date at once. > It connects to AI assistants over the Model Context Protocol. One ad is a single frame. This shows the whole body of work. Endpoint: https://mcp.spytrend.com/mcp — Streamable HTTP, browser sign-in with a Spytrend account. Nothing to install, no key to paste. The connection is available on every plan, though the free plan is limited to the archive — nothing from the last 90 days. Usage is metered in tokens from one balance and you pay for results, not for asking: a call that returns nothing costs nothing. Ask get_usage — it is free and it answers from the server. Ads can be filtered by country, business category, format and run dates. Advertising is sorted into business categories — home services, beauty, games, finance, education and so on — so you can look at your own niche instead of everything at once. ## Connect - [Connection page](https://spytrend.com/mcp/?utm_source=github&utm_medium=repo&utm_campaign=mcp-launch): endpoint, sign-in and per-client setup - [Quickstart](https://github.com/Spytrend/spytrend-mcp/blob/main/docs/quickstart.md): connecting in five minutes, per client - [Repository](https://github.com/Spytrend/spytrend-mcp): connection passport, tool reference and recipes ## Tools - [Tool reference](https://github.com/Spytrend/spytrend-mcp/blob/main/docs/tools.md): every documented tool, when to use it and when not to - Search: `search_ads`, `search_creatives`, `search_advertisers`, `search_webmasters`, `search_hubs`, `search_shops` - One record in full: `get_ad`, `get_advertiser`, `get_webmaster`, `get_creative`, `get_shop` - Download: `get_media` — the image or video file itself - Rankings: `get_trends` - Look-alikes: `find_similar_ads`, `find_similar_creatives`, `find_similar_webmasters`, `get_webmaster_similarity_facets` - Folders and balance: `add_to_favorites`, `list_favorites`, `get_usage` - Twenty-one tools in all. Costs are in the tool reference; `get_usage` always answers from the server. ## Recipes - [Find competitors](https://github.com/Spytrend/spytrend-mcp/blob/main/examples/find-competitors.md): who else is advertising in your market, and what they run - [Match to a business type](https://github.com/Spytrend/spytrend-mcp/blob/main/examples/by-business-type.md): advertising from businesses like yours, no competitor names needed - [Top of a niche](https://github.com/Spytrend/spytrend-mcp/blob/main/examples/top-of-niche.md): what is running in a category, by how long it has been up - [What is running now](https://github.com/Spytrend/spytrend-mcp/blob/main/examples/running-now.md): what is new and picking up in an industry ## Skills - [Skills](https://github.com/Spytrend/spytrend-mcp/tree/main/skills): six ready-made workflows for Claude Code and Codex — vertical intelligence, advertiser overview, webmaster overview, website review, keyword search, shop discovery. Plain folders; copy into the assistant's skills directory. - [Connection manual for agents](https://mcp.spytrend.com/llms.txt): token flow, per-client connection paths, access and billing, straight from the server. ## Product - [Plans](https://spytrend.com/pricing/?utm_source=github&utm_medium=repo&utm_campaign=mcp-launch): Starter free, Pro, Team, Enterprise - [Limits and tokens](https://github.com/Spytrend/spytrend-mcp/blob/main/docs/limits.md): what each call costs, what is free, what the assistant sees when the balance runs out - [Contact and support](https://spytrend.com/contact/): questions about connecting, access and accounts - [Privacy policy](https://spytrend.com/legal/privacy/) - [Terms of service](https://spytrend.com/legal/terms/) ## Optional - [Blog](https://spytrend.com/blog?utm_source=github&utm_medium=repo&utm_campaign=mcp-launch): background reading
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

