Agentscore

io.github.ThezenmonsterPublished by GitHub account Thezenmonsterv2.2.0Updated Oct 27, 2026

MCP security trust layer: scan packages, inspect repos, check exposure, monitor changes.

VerifiedSTDIODesktop onlyDeveloper Tools Security & Monitoring

Server details

Identifier: io.github.Thezenmonster/agentscore
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account Thezenmonster for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.Thezenmonster%2Fagentscore.svg)](https://sourceweft.com/mcp/io.github.Thezenmonster%2Fagentscore?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

AgentScore MCP server that lets an assistant scan MCP packages for security issues, get allow/warn/block trust verdicts, and check incident exposure.

What you can do: Scan and rate packages: full security scan of install scripts, prompt injection, source patterns and provenance, plus a trust verdict with risk score
Inspect a local repository for MCP dependencies and summarise verdicts for each detected package
Generate or write a GitHub Actions Policy Gate workflow file into the repo for CI enforcement
Incident response: find monitored MCP servers that depend on a given package, and query an abuse database for reported packages or agents
Check whether a package is under continuous monitoring and view its scan history
When to use it: Useful when deciding whether an MCP package or server is safe to install, when auditing a repository's MCP dependencies, or when a dependency is compromised and you need to know which MCP servers are affected. Also fits teams that want to turn one-off checks into a CI policy gate.
Requirements: Runs locally over stdio, typically started with npx from the npm package @agentscore-xyz/mcp-server, so Node.js and network access are needed. The README states no API key and zero config; the manifest declares no environment variables or headers. Writing the CI workflow requires a GitHub repository.

Before you install

install_policy_gate writes a workflow file into the repository's .github/workflows directory, which changes project files and should be reviewed before committing. Package scans and verdicts are sent to the provider's service, and the first CI run auto-provisions the repo through GitHub OIDC. Verdicts are advisory scores, not a guarantee of safety.

Installation

In SourceWeft

Open Agentscore in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@agentscore-xyz/mcp-server

MCP security trust layer. Scan packages, get trust verdicts, inspect repo-wide MCP dependencies, generate Policy Gate setup, install the CI workflow directly, check incident exposure, and query the abuse database. Eight tools for MCP security decisions. No API key, zero config.

[KYA Scan]

Scan any MCP package for security issues: agentscores.xyz

Quick Start

Claude Desktop

Add to your claude_desktop_config.json:

json

{  "mcpServers": {    "agentscore": {      "command": "npx",      "args": ["-y", "@agentscore-xyz/mcp-server"]    }  }}

{  "mcpServers": {    "agentscore": {      "command": "npx",      "args": ["-y", "@agentscore-xyz/mcp-server"]    }  }}

Cursor / Any MCP Client

What This Does

Your AI can now make security decisions about MCP packages:

You: "Is exa-mcp-server safe to install?"

Claude: calls get_verdict "Verdict: ALLOW. Score 90/100, LOW risk. No provenance attestations (published by personal account). 9 tools exposed including web_search_exa and crawling_exa."

You: "The axios package was compromised. Which MCP servers are affected?"

Claude: calls check_exposure "Multiple monitored MCP servers depend on axios, including exa-mcp-server, tavily-mcp, and figma-mcp."

You: "Scan @azure-devops/mcp for security issues"

Claude: calls scan_package "Score 75/100, MODERATE risk. Found: preinstall script modifying npm registry config. No provenance attestations."

You: "Check this repo for MCP dependencies"

Claude: calls check_my_repo "MCP dependencies found: 5. Two are warnings. Run generate_policy_gate_setup to turn these checks into a CI gate."

You: "Set up AgentScore Policy Gate for this repo"

Claude: calls install_policy_gate "The workflow file is written to .github/workflows/agentscore-policy-gate.yml. Commit and push. GitHub OIDC will auto-provision the repo on first run."

Available Tools

Tool	What it does
`scan_package`	Full security scan: install scripts, prompt injection, source code patterns, provenance posture, MCP tool extraction
`get_verdict`	Trust decision: allow, warn, or block based on scan findings. Also reports monitoring status and publisher posture.
`check_my_repo`	Inspect the current repo for MCP dependencies and summarise verdicts for every package detected locally.
`generate_policy_gate_setup`	Generate the exact OIDC-based GitHub Actions workflow needed to enforce Policy Gate in CI.
`install_policy_gate`	Write `.github/workflows/agentscore-policy-gate.yml` directly into the repo so the gate is ready to commit.
`check_exposure`	Incident response: which monitored MCP servers depend on a given package?
`check_abuse`	Query the KYA abuse database for reported packages or agents
`monitor_status`	Check if a package is under continuous monitoring and get scan history

From Ad-Hoc Scans To CI Enforcement

The MCP server now bridges one-off package checks into the sticky product:

Run check_my_repo to see every MCP package used in a repo.
Run generate_policy_gate_setup to preview the OIDC-based GitHub Actions workflow.
Run install_policy_gate to write the workflow file directly into the repo.
Commit and push. The first run auto-provisions through GitHub OIDC.

That turns "is this package safe?" into "this repo now enforces MCP dependency policy on every PR."

Risk Levels

Score	Risk	Meaning
85-100	LOW	Clean or minor issues only
70-84	MODERATE	Some findings, review recommended
50-69	ELEVATED	Significant findings, use with caution
30-49	HIGH	Serious issues, not recommended
0-29	CRITICAL	Do not use

What the Scanner Checks

Install scripts (postinstall/preinstall hooks with network calls or code execution)
Prompt injection patterns in package metadata
Suspicious URLs (sketchy TLDs, ngrok, raw IPs)
Source code patterns (command injection, unsafe eval, hardcoded secrets)
Publisher provenance (trusted publishing, attestations)
Dependency count and metadata completeness
MCP tool definitions extracted from published source

Monitoring

AgentScore continuously monitors hundreds of MCP packages. The check_exposure and monitor_status tools use this live dataset. When a package like axios gets compromised, you can instantly find which MCP servers are affected.

Licence

MIT

Source: README.md at commit c6c930c

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v2.2.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts