
Pushbuild MCP server
Which MCP servers are Pushbuild's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-11-03
- Registry namecom.pushbuild/data-apisverified in the MCP registry
The registry name sits under pushbuild.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-03
- Tools3
- Server calls itselfpushbuild-apis
- Server version1.0
- Protocol version2025-06-18
On 2026-11-03 the server answered initialize and tools/list without a sign-in. First answer in 244 ms.
- Its tools do none of the product's use cases we checked: reply to new leads from web forms and missed calls; log WhatsApp chats as notes in the CRM.
- Checked on 1 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- What an agent can do with it0 of 2 use cases
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer513 ms
- Space in an agent's context≈ 268 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- cannot · reply to new leads from web forms and missed calls
- cannot · log WhatsApp chats as notes in the CRM
- not sure · post supplier invoices into QuickBooks or Xero bills
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_apisFind Pushbuild data APIs by keyword (e.g. 'campaign contributions texas', 'restaurant inspections', 'sec 13f'). Returns api ids, what each covers and price per record. Free.
describe_apiInput parameters (JSON Schema), coverage and price for one API id from search_apis. Free.
call_apiRun one API with parameters from describe_api. Returns JSON records (default 25; set maxItems up to 500). Billed per record from the key's free allowance, then credit.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"data-apis": {
"type": "http",
"url": "https://api.pushbuild.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http pushbuild https://api.pushbuild.com/mcpclaude.ai, ChatGPT and other clients: add https://api.pushbuild.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.