Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Argentic
MCP serversArgentic MCP server: run and inspect long-running agents on Argentic.
-
Omada-mcp
MCP serversSecurity-first MCP server for TP-Link Omada, with a stdio-first runtime, capability-gated tools, and OpenAPI-based network automation.
git clone https://github.com/gaspareduard/Omada-mcp.git -
suitest
MCP serversSelf-hostable, MCP-native testing platform. Manual test management, deterministic runs, optional AI. Your stack, your LLM, your data.
git clone https://github.com/suiflex/suitest.git -
luma-mcp
MCP serversRunAPI MCP server for Luma: query historical tasks.
@runapi.ai/luma-mcp@0.3.1 -
NetSuite Link (beta)
MCP serversBETA — Run SuiteQL, read/write NetSuite records, query SuiteAnalytics, and run saved bookmarks.
-
pare-make
MCP serversPare Make ג€” Structured Make/Just task runner operations (run, list) as typed JSON.
@paretools/make@0.8.1 -
CarMaker
MCP serversDrive IPG CarMaker for Simulink: run test runs, read results, edit vehicle data and parameters.
carmaker-mcp@0.2.1 -
mcp-trace-inspector
MCP serversRead local agent-run JSONL traces through MCP for failures, approvals, and run comparisons.
mcp-trace-inspector@0.3.1 -
mcp-multi-poc-beta-script
MCP serversPoC Q5b: run a differently-named console script via a positional runtimeArgument.
mcp-multi-poc@0.1.0 -
agentl
MCP serversValidate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs.
agentl-etl@0.9.0 -
k6-mcp
MCP serversQuery a running k6: runtime status and metric list. Endpoints per k6 REST API docs.
k6-mcp@1.0.0 -
CarMaker
MCP serversDrive IPG CarMaker for Simulink: run test runs, read results, edit vehicle data and parameters.
carmaker-mcp@0.3.0 -
Recipe360
MCP serversYour AI runs your data workflows the same way every time, with a record of every run.
https://github.com/sebastianarangouribe-coder/recipe360-mcp/releases/download/v0.1.0-rc.9/recipe360.mcpb -
CronObserver
MCP serversKnow when cron jobs and AI agents stop running: monitors, check-ins, incidents and runbooks.
-
kali-mcp-go
MCP serversMCP runtime for AI-assisted security testing with Kali tools, explicit target controls, bounded scanning, structured evidence, and persistent Docker deployment.
git clone https://github.com/found-cake/kali-mcp-go.git -
cinch
MCP serversRun AI-generated code safely. gVisor-isolated Python/JS sandboxes for any MCP client. Pay per run.
@cinch-codes/mcp@0.1.1 -
Inngest MCP by usefulapi
MCP serversTrace events to function runs to the failing step, and bulk-cancel runs.
-
OTInstaller
MCP serversInstall and run open-source OSINT tools in a local sandbox, asking before runs that touch a target.
https://github.com/OTInstaller/ot/releases/download/v0.16.1/ot_0.16.1_darwin_amd64.mcpb@0.16.1 -
evalpair
MCP serversRun LLM eval suites on local or hosted models; compare runs with intervals and a noise floor.
evalpair@0.1.1 -
Koschei
MCP serversRun agent-written code under a capability policy: see what a program can touch before it runs.
koschei-lang@0.14.0 -
mcp
MCP serversRunSec MCP server for workspace security scanning and remediation workflows.
@runsec/mcp@1.0.127 -
inference.sh
MCP serversrun any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.
-
Pipe2.ai
MCP serversRun multi-step AI pipelines for video, image, audio and text: upload media, run, poll results.
-
ChargerDojo
MCP serversOCPI versions, checks and payload validation, plus your own test runs and run starts with a key.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.