
Promptafire MCP server
Which MCP servers are Promptafire'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 2026-10-25
- Registry namecom.promptafire.marketing/promptafireverified in the MCP registry
The registry name sits under promptafire.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-25
- Tools8
- Server calls itselfpromptafire
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 116 ms.
- Its tools do none of the product's use cases we checked: Draft nurture email sequences that sound human; Write campaign briefs from a single rough idea; Build landing pages and performance dashboards with AI tools.
- Checked on 3 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: 3 so far
- What an agent can do with it0 of 3 use cases
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer138 ms
- Space in an agent's context≈ 695 tokensthe definitions of all its tools (8), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results2 of 8 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- cannot · Draft nurture email sequences that sound human
- cannot · Write campaign briefs from a single rough idea
- cannot · Build landing pages and performance dashboards with AI tools
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 →
searchSearch Promptafire lessons and blog posts. Returns ids for fetch, titles, and web URLs. Lesson ids look like lesson:<module>/<section>, post ids like post:<slug>.
fetchReturn the full Markdown of one search result by id. Free lessons and blog posts always; Pro lessons only when the connected Promptafire account has Pro access, otherwise a short locked notice.
search_curriculumFull-text search across Promptafire lessons. Returns module, section, whether it is free or Pro, a short snippet when readable, and the web URL.
list_modulesThe full curriculum: every track and module with its access level and a link to its overview.
get_moduleA module's description, duration, access level, and section list.
read_lessonThe Markdown body of one lesson section. Free modules always. Pro modules only when the connected Promptafire account has Pro access.
list_postsEvery published Promptafire blog post with date, author, and a link.
read_postThe Markdown body of one blog post.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"promptafire": {
"type": "http",
"url": "https://marketing.promptafire.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http promptafire https://marketing.promptafire.com/api/mcpclaude.ai, ChatGPT and other clients: add https://marketing.promptafire.com/api/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.
Cookies
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.