
99tests MCP server
Which MCP servers are 99tests'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 2026-11-04
- Registry namecom.99tests/mcpverified in the MCP registry
The registry name sits under 99tests.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-04
- Tools5
- Server calls itself99tests
- Server version1.0.0
- Protocol version2024-11-05
On 2026-11-04 the server answered initialize and tools/list without a sign-in. First answer in 186 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Once connected
- create_test_job change data without a sign-in: anyone with the address can call them.
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
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer374 ms
- Space in an agent's context≈ 378 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
Worth a look
- Tools that change data, on a server that answers without a sign-in: create_test_job
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 →
list_packagesList 99tests packages, prices (INR + GST and USD), session counts, devices and turnaround.
create_test_jobCreate a 99tests test job and return a hosted checkout link to pay in a browser. Never charges a card directly.
get_job_statusCheck a job's stage and progress using the customer's own status link or token. Poll at most every 10 minutes.
get_reportGet the verified findings for a delivered job as ready-to-paste fix prompts, using the customer's own status link or token.
get_sample_reportGet a description and link to an example 99tests report, so you can see the format before paying.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"99tests": {
"type": "http",
"url": "https://99tests.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http 99tests https://99tests.com/api/mcpclaude.ai, ChatGPT and other clients: add https://99tests.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.
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.