$ loading_
Lets AI agents discover, register, and rate services in a decentralized directory.
This MCP tool has sparse documentation, declares no required secrets or remote endpoints, and is open source and auditable, with no clear high-risk red flags observed. The main uncertainties are missing documentation, low community adoption, and unclear local permission boundaries inherent to a runnable MCP service.
The materials explicitly state that no keys or environment variables are required, and no API key, token, or other sensitive credential is mentioned; based on the available information, credential exposure or abuse risk appears low.
No remote endpoint is declared, and the materials provide no concrete egress destination; however, the stated functionality of discovering/registering/rating services in a decentralized directory could imply network interaction. With no README, it cannot be verified whether user data is sent anywhere.
System checks indicate that this tool executes code; as an MCP service, this typically means starting a local process and running its logic. The available materials do not show requests for system privileges beyond its stated purpose, so this is rated as caution for standard execution capability.
The documentation does not specify what local files, directories, or other resources it can read or write, so minimum-privilege boundaries cannot be confirmed. As a locally running MCP tool, the data surface available to its runtime account should be noted, but there is no explicit evidence of overbroad access in the materials.
Positive factors include being open source under MIT and having auditable source code, which materially lowers supply-chain risk; however, it comes from a third-party registry, the GitHub repo has 0 stars, maintenance status is unknown, and the README is absent, so maturity and ongoing maintenance remain unclear. This supports a caution rating rather than high risk.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Agent Directory MCP Server" yet — see the docs or source repo.
Find AI agent services in the Agent Directory for web scraping and summarization, rank them by rating and availability, and return their names, purposes, API details, and ratings.
A filtered and ranked list of agent services with key details and rating comparisons.
Register my AI agent in the Agent Directory: its name is 'ReportGen Bot', it generates weekly reports automatically, and supports Markdown output. Prepare a proper registration entry and submit it.
A structured agent registration record including name, capability description, tags, and submission status.
I just used a code review agent service. Based on this experience, generate a review and submit it to the Agent Directory: fast response, professional suggestions, but occasionally misses security issues; overall rating 4 stars.
A standardized service review ready to submit, including rating, strengths, weaknesses, and a brief summary.
Register, discover, rate, and manage AI agents and services locally.
Orchestrate multiple AI agents in real time and monitor tasks and artifacts.
Enable AI agents to communicate, route messages, and collaborate through MCP.
Expose reusable team skills to MCP agents via package.json configuration.
Securely connect AI agents to PostgreSQL with role-based database access.
Add agentic tools with iterative reasoning and tool use to apps