MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Code & DevOps

JMeter Docs

Apache JMeter community documentation, conversion tools, linters, and calculators for AI agents.

Checks passed
14 / 22

1 failed · 7 not measured

Median response
400 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
16

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
103
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
310
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 396 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name jmeter-docs.

  • Pass
    Lists tools

    tools/list returned 16 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 400 ms over 2 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 403 ms over 2 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    2 of 2 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Pass
    Stable tool list

    No tool was removed and no required parameter was added in the last 30 days.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    66 of 66 parameters have a description (100%). The bar is 80%.

  • Fail
    Safety hints

    16 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Pass
    Repo owner matches

    The GitHub repository owner matches the namespace login.

  • Pass
    Recently updated

    Updated 2026-09-08T14:54:13.675457Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using JMeter Docs

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http jmeter-docs https://docs.jmeter.ai/api/mcp

Capabilities

Tools 16

calculate_workload_model

Compute required thread concurrency, pacing delays, ramp-up schedules, and JVM heap recommendations based on target RPS/TPS and SLA response times using Little's Law.

Discovered
convert_curl_or_har_to_jmx

Convert one or more cURL commands or HAR (HTTP Archive 1.2) JSON traces into a valid, production-ready Apache JMeter .jmx test plan XML with HTTP Request Defaults, Header Managers, Cookie Managers, timeouts, and assertions. Supports GET, POST, PUT, DELETE, PATCH, and RFC 9838 QUERY methods.

Discovered
convert_openapi_to_jmx

Convert an OpenAPI 3.0/3.1 or Swagger 2.0 document (JSON or YAML) into a JMeter 5.6.3 .jmx test plan: servers become HTTP Request Defaults/${BASE_URL}, path parameters become User Defined Variables, request bodies are sampled from schemas, bearer/basic/apiKey security becomes ${AUTH_TOKEN}/${BASIC_AUTH}/${API_KEY}, with optional method, tag, and deprecated-operation filters.

Discovered
get_correlation_sandbox

Generate a ready-to-run Apache JMeter 5.6.3 .jmx practice test plan (either "solved" with Boundary/JSON/Header extractors or "challenge" with broken hardcoded tokens) targeting the live docs.jmeter.ai/api/sandbox endpoints or local localhost:8787 server.

Discovered
get_jmeter_page

Fetch the full markdown text of one docs.jmeter.ai page. Accepts the page URL (e.g. https://docs.jmeter.ai/topics/api-load-testing/) or a bare path (e.g. topics/api-load-testing).

Discovered
get_jsr223_recipe

Fetch production-ready, performant Groovy scripts for JMeter JSR223 samplers, preprocessors, and postprocessors (e.g., JWT parsing & expiration, HMAC-SHA256 signing, dynamic header injection, nested JSON array extraction, custom CSV failure logging).

Discovered
lint_groovy_script

Statically analyze a Groovy script for a JMeter JSR223 element. Flags Thread.sleep, ${var} interpolation, System.out, BeanShell APIs, per-call Random or Pattern.compile, and bindings such as prev, SampleResult, or sampler that the selected element type does not expose; optionally returns ready-to-paste JMX element XML.

Discovered
lint_jmx_snippet

Validate a JMeter test plan XML string or snippet against best practices and performance anti-patterns, and return a structural inventory with thread groups, sampler/listener/assertion counts, HTTP Defaults/Header/Cookie/CSV presence, plugin classes, and JMeter version.

Discovered
lookup_component

Find the dedicated reference page for a JMeter test plan component (e.g. "HTTP Request", "JSON Extractor", "Thread Group") and return its full markdown content with properties, defaults, and related guides.

Discovered
lookup_error_playbook

Get immediate root causes, OS/JVM config fixes, and remediation steps for common JMeter exceptions (e.g. "BindException", "SocketTimeoutException", "OutOfMemoryError", "NoHttpResponseException", "SSLHandshakeException", "401/403 after recording"). When keywords miss, unmatched text is sent to classifier.dev for zero-shot semantic matching (public keyless calls are not stored).

Discovered
lookup_function

Find the dedicated reference page for a built-in JMeter function (e.g. "__time", "__Random", "__P") and return its full markdown content with syntax, parameters, and examples.

Discovered
lookup_jmeter_property

Search or lookup curated JMeter properties (e.g. "httpclient4.idletimeout", "jmeter.save.saveservice.*", "remote_hosts", "summariser"). Returns category, defaults, and recommendations.

Discovered
plan_distributed_testing

Generate Master-Worker RMI port assignments, user.properties, CLI commands, firewall/security group rules, and Docker Compose manifests for distributed load testing.

Discovered
search_jmeter_docs

Search the Apache JMeter documentation on docs.jmeter.ai. Returns the most relevant pages with titles, URLs, and snippets. Use for any question about JMeter test plans, components, functions, properties, distributed testing, reports, or troubleshooting.

Discovered
triage_errors

Map a run's distinct failure signatures to docs.jmeter.ai error playbooks. Error text is sent to classifier.dev for zero-shot classification (public keyless calls are not stored; obvious secrets are redacted first). Prefer signatures shaped as "sampler | response code | response message".

Discovered
tune_linux_os

Generate production sysctl.conf, limits.conf, systemd overrides, and Docker/K8s configs tuned for high-concurrency JMeter load testing (fixing ulimit nofile, BindException port exhaustion, somaxconn backlog, and JVM swappiness).

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected396 ms16
Connected403 ms16