Search Facebook ads, decode competitor creative strategy, and track brand ad history.
Spresh MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Search Facebook ads, decode competitor creative strategy, and track brand ad history.
MCP server that connects Claude to SpreshApp's Facebook ad intelligence platform.
The server ships on npm as spreshapp-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Once Spresh is connected, these are the calls the assistant has available:
ad_search — Search Facebook ads by keyword, niche, or industryad_search_expand_query — Expand a search query to surface more relevant adsad_get — Fetch full details for a specific adad_get_analysis — Retrieve saved AI analysis for an adad_analyze — Run AI analysis on any adad_analyze_batch — Analyze multiple ads in one callad_chat — Chat with Claude about an ad's creative strategybrand_search — Search for brands in SpreshAppbrand_get_overview — Get a brand's full profile and statsbrand_get_status — Get the current tracking status for a brandbrand_get_ad_history — Get historical ad volume data for a brandbrand_list_active_ads — List all ads a brand is currently runningYou will need 4 environment variables: SPRESHAPP_API_KEY, SPRESHAPP_ACCESS_TOKEN, SPRESHAPP_REFRESH_TOKEN, SPRESHAPP_CLIENT_ID. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Spresh's toolset — ad_search, ad_search_expand_query, ad_get and 11 more — is a fair guide to whether it matches your workflow. It is maintained by PrashantBtkl; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| ad_search | Search Facebook ads by keyword, niche, or industry |
| ad_search_expand_query | Expand a search query to surface more relevant ads |
| ad_get | Fetch full details for a specific ad |
| ad_get_analysis | Retrieve saved AI analysis for an ad |
| ad_analyze | Run AI analysis on any ad |
| ad_analyze_batch | Analyze multiple ads in one call |
| ad_chat | Chat with Claude about an ad's creative strategy |
| brand_search | Search for brands in SpreshApp |
| brand_get_overview | Get a brand's full profile and stats |
| brand_get_status | Get the current tracking status for a brand |
| brand_get_ad_history | Get historical ad volume data for a brand |
| brand_list_active_ads | List all ads a brand is currently running |
| brand_follow | Start tracking a brand |
| search_ads | Search your saved ad library |
{
"mcpServers": {
"spreshapp": {
"command": "npx",
"args": ["-y", "spreshapp-mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| SPRESHAPP_API_KEY | Credential the server authenticates with. | Yes |
| SPRESHAPP_ACCESS_TOKEN | Credential the server authenticates with. | Yes |
| SPRESHAPP_REFRESH_TOKEN | Credential the server authenticates with. | Yes |
| SPRESHAPP_CLIENT_ID | Configuration value read at startup. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.