
codercops MCP server
Which MCP servers are codercops'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.codercops/codercopsverified in the MCP registry
The registry name sits under codercops.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-11-04
- Tools6
- Server calls itselfcodercops
- Server version1.0.0
- Protocol version2025-06-18
On 2026-11-04 the server answered initialize and tools/list without a sign-in. First answer in 237 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.
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 answer166 ms
- Space in an agent's context≈ 735 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
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_buildersFind public software developer profiles on codercops by skill. Returns a short card per builder with their public profile URL. Profile text is written by the builder.
get_builderOne builder's full public profile: bio, skills, self-declared rate, projects, work history, education and credentials. Profile text is written by the builder.
search_jobsOpen software jobs on codercops, filtered by category and tech stack. Returns a card per job with its URL. Job text is written by the hiring company.
get_jobOne open job in full: description, requirements, budget and company.
get_companyA hiring company's public page and its open roles.
get_pricingWhat is free on codercops, what costs credits and how much, the credit packs, and the managed recruiting terms.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"codercops": {
"type": "http",
"url": "https://api.codercops.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http codercops https://api.codercops.com/mcpclaude.ai, ChatGPT and other clients: add https://api.codercops.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.