offprompt
MCP serverCollect API keys in a browser page and write them to .env without the model seeing them
Runs locally- 1 tool
- Open source
- Security
Collect API keys in a browser page and write them to .env without the model seeing them
Runs locally
Safe writes, find-usages and instance drift checks for ServiceNow through an MCP server
Not checked yet
Fault-injection MCP server for testing how MCP clients handle timeouts and bad replies
Runs locally
Wraps any MCP server so repeated write calls run once and every call is logged
Runs locallyLet AI coding agents work through visual annotations on a live webpage
Runs locallyGo server giving assistants GitLab merge request, pipeline and issue actions
Not checked yetDraw AWS, Azure and GCP architecture diagrams from a prompt or Terraform code
Runs locally
Security checks for coding agents: dependency audits and evidence for fixes
Not checked yetRead-only Ansible checks for agents: installed module specs, task args, upgrade impact
Runs locallyFlags hardcoded colours and unknown components in agent-written React UI code
Runs locallyFind open-source projects worth contributing to and the work they need
Runs locallyOffline dev utilities for agents: UUIDs, hashes, JWT decoding, cron and regex tests
Runs locallyLet an AI assistant operate Java Swing and JavaFX desktop apps with no API needed
Runs locallyLive weather, WHOIS, DNS, SSL, IP and other lookups from APIFreaks, enabled by module
Runs locallyCheck AI-written documents against versioned contracts before release, with audit evidence
Runs locallyRead-only Apache NiFi investigation that cites evidence and drafts flow changes
Runs locallyUnofficial hosted MCP server for managing Infomaniak DNS, mail and VPS apps
Not checked yetReal Kotlin and Java library sources, API signatures and KDoc from Maven sources jars
Runs locallyLocal twins of the Jobber, Housecall Pro and QuickBooks APIs for testing agents
Runs locallyLocal persistent memory for coding agents, with a temporal knowledge graph
Runs locallyVerify a running web app from inside: look, act, observe and assert, without screenshots
Runs locallyRecord approved project decisions and their reasons so coding agents recall them later
Runs locallyLet an assistant inspect and operate Spinnaker pipelines through the Gate API
Runs locallyLet agents read, search and edit a self-hosted architecture model over MCP
Not checked yet39 WCAG 2.2 scanners for web pages, Office, PDF and ePub files in any MCP client
Runs locallyLocal, append-only agent memory that records who said what and keeps conflicts visible
Runs locallyStructural change control and code-health analysis for AI-assisted Python development
Runs locallyRenders dashboards, forms and tables inline in chat as Angular Material components
Not checked yet
One gateway that lets AI agents operate Maya, Blender, Houdini and dozens of other apps
Not checked yet
Generate an llms.txt from Markdown or a sitemap and check an existing file
Runs locally