mcpbeat Sign in

Keploy MCP Server

answering

Keploy is answering right now. Last checked 4 min ago. It exposes 7 tools. Last commit 17 Sep 2026.

End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic.

Uptime history 47 days of history
47 days agonow
100.0%
Uptime 24h
92 of 92 checks
7
Tools
read from the server
622 ms
Response time
average over 24h
18465
Stars
last commit 17 Sep 2026

What the code does

We read the source, 20 h ago · tools taken from the live server · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a database query by concatenation pkg/agent/proxy/integrations/mysql/replayer/query.go:50
        select {
        case <-ctx.Done():
            return ctx.Err()
        default:
            commandCount++

            // logger.Debug("Starting new command iteration",
            // zap.Int("command_count", commandCount))

            // Set a read deadline on the cl…
    mappingPath := filepath.Join(db.path, testSetID)
Asks for container control access cli/provider/cmd.go:75
    alias keploy='sudo docker run --name keploy-ebpf -p 16789:16789 --privileged --pid=host -it -v $(pwd):$(pwd) -w $(pwd) -v /sys/fs/cgroup:/sys/fs/cgroup
    GenericRequests  []Payload         `json:"RequestBin,omitempty"`
In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Touches key and credential files .github/actions/setup-private-parsers/action.yaml:57
        cat <<'EOF' >> ~/.ssh/known_hosts

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.

run in your terminal
claude mcp add mcp --transport http https://api.keploy.io/client/v1/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.keploy.io/client/v1/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.mcp]
url = "https://api.keploy.io/client/v1/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.keploy.io/client/v1/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://api.keploy.io/client/v1/mcp"
    }
  }
}

Available tools 7

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

devloop
devloop_begin_oauth_install
Start the Path B agent-walked install for the V1 flow. Returns a playbook the AI walks with the dev to land a kep_* PAT in their editor's MCP config. Current implementation routes through app.keploy.io/settings/api-keys (the existing PAT-issuance surface). The full auto-provision OAuth round-trip (browser OAuth → /auth/temp-code/exchange → /user/mcp/provision → PAT auto-pasted) lands when the enterprise-ui /auth/cli-install page is built; this tool's interface won't change when that lifts, only the underlying steps will get shorter. ABSOLUTE: this tool surfaces a public URL. Do NOT print API keys, PATs, or OAuth tokens to the conversation. The dev pastes the secret into their editor config directly; the agent never sees it.
devloop_setup_instructions
Return the V1 "user maintains the flow" install guide — covers Path A (clipboard one-liner), Path B (agent-walked OAuth), and the keploy/api-tests/ on-disk layout V1 creates. Safe to call without authentication; call this when the dev asks 'how do I add Keploy to this repo?' or when a devloop_* tool returns missing-API-key.
auth
get_auth_status
Check whether the current MCP session has a valid-looking Keploy PAT attached. Returns { authenticated, auth_header_present, hint }. Useful as a first step for an agent to decide whether to call other tools or show setup instructions — differentiates 'no header at all' from 'header present but wrong prefix / unsupported format'.
invoke
invoke_tool
Run any Keploy tool by name. Most tools are hidden from the default list. Know the name from a skill? get its schema with get_tool_schema; don't know the name? discover it with search_tools. Then call invoke_tool with that name and an "arguments" object matching the tool's inputSchema. Example: invoke_tool {"name": "getTestReportFull", "arguments": {"appId": "...", "testRunId": "...", "fields": ["status"]}}
setup
get_setup_instructions
Return step-by-step instructions for connecting this MCP server to Cursor, Windsurf, VS Code, Claude Desktop, Claude Code, or Trae. Safe to call without authentication — use this when the user asks 'how do I set up Keploy MCP?' or when a tool call fails with an auth error.
tool
get_tool_schema
Fetch the exact schema(s) for tool(s) you ALREADY know by name — e.g. names a skill/playbook gave you (getTestReportFull, updateTestCase, listTestReports, getMock, getTestCase, getApp, listApps, ...). Returns ONLY the named tools: no fuzzy matching, no unrelated tools. Use this instead of search_tools whenever you know the name — it is exact and cheap. Use search_tools only to DISCOVER names you do not already know. Returns {"tools": [{name, description, inputSchema}, ...], "not_found": [names...]}.
tools
search_tools
DISCOVER tool names you do NOT already know, by keyword. Most Keploy tools are hidden from the default tool list to save context. If you ALREADY know the exact name (e.g. a skill named it), call get_tool_schema instead — it is exact and far cheaper than this fuzzy search. Returns {"matches": [{name, description, inputSchema}, ...], "total_catalog": N}. Search by intent words, e.g. "test report", "mock patch", "update test case", "cloud replay branch", "record".

Endpoints

URLTransportStateLatencyChecked
https://api.keploy.io/client/v1/mcp streamable-http answering 611 ms 4 min ago

Alternatives to Keploy

same job, measured the same way
Smolanalytics
by arjun0606

End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.

166 installs/wk local only
API Tester
by ryudi84

MCP server for API testing: HTTP requests, cURL generation, health checks.

31 installs/wk local only
I
MCP API Doc Generator
by vpatser1

Generate OpenAPI 3.1 specs, endpoint docs, TypeScript SDKs, and test suites from code

28 installs/wk local only
Synthetic Data — Random User
by saifs

Generate synthetic random user data for testing, demos, and development without using real persona.

answering
Cloud Agent
by joepangallo

AI software engineer — writes code, opens PRs, reviews code, generates tests, and more.

35 installs/wk local only
Connic
by connic

Build, test, deploy, and operate Connic agents.

answering
Random Profiles
by random-profiles

Generate fake user profiles and companies for tests, seed data, and AI agent demos.

59 installs/wk local only
JsonFabrica
by ms-methos

Generate realistic, relational synthetic JSON test data from templates, via the JsonFabrica API.

87 installs/wk local only

Keploy — questions

Answers built from our own checks of this server.

What can Keploy do?
It exposes 7 tools, read directly from the server on our last check. Among them: devloop_begin_oauth_install, devloop_setup_instructions, get_auth_status, get_setup_instructions, get_tool_schema, invoke_tool and 1 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Keploy working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 622 ms. The bar chart above shows every period we have measured.
How do I connect Keploy?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Keploy need an API key?
No. Keploy completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 7 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Keploy?
It answers our handshake in 622 ms on average, which is faster than 20% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Keploy open source?
Yes — it is published under the Apache-2.0 licence, written in Go, 18 465 stars on GitHub and 358 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.