Skip to content
Agentmart
Submit a tool

MCP Safeguard

MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

Connector by cognivators.com · Domain verified by the MCP Registry

IndexedLicense unknownLocal (stdio)
Write a review

Chalk Labs

Need help deploying MCP Safeguard?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/cognivators-com-mcp-safeguard

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
6 read · 0 write · 0 delete · 1 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 7

Read from the source code; the running server may list different tools.

Read 6 · Look things up without changing anything.

  • check_auth_config
  • check_endpoint_exposure
  • compare_scans
  • generate_security_report
  • get_scan_history
  • scan_tool_definitions

Not yet classified 1 · We could not tell from the name and description.

  • scan_mcp_server

Network hosts it talks to 4

  • 169.254.169.254 · found in code
  • attacker.com · found in code
  • github.com · found in code
  • gitlab.com · found in code

Files it touches

  • /tmp/mcp-shield-reports

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • check_auth_config

    Audit an MCP server configuration for credential exposure and OAuth scope risks. Args: config_json: JSON string of the server configuration (e.g. Claude Desktop config entry). Returns: Dict with credential_findings, oauth_findings, and a risk summary.

  • check_endpoint_exposure

    Probe an MCP server for exposed admin panels, debug routes, and dangerous ports. Only scans localhost and explicitly allowlisted hosts (SSRF protection). Args: host: Hostname or IP to scan (must be in SSRF allowlist). port: Port number the MCP server is running on. Returns: Dict with endpoint_findings and open_ports.

  • compare_scans

    Compare two security scans to identify regressions or improvements. Args: scan_id_1: UUID of the baseline scan. scan_id_2: UUID of the comparison scan. Returns: Diff showing new findings, resolved findings, and score changes.

  • generate_security_report

    Retrieve a full security report for a completed scan. Args: scan_id: UUID of the scan to retrieve. format: "json" (default), "html", or "text". Returns: The full report in the requested format.

  • get_scan_history

    List all past scans with their severity scores and targets. Returns: Dict with a list of scan summaries, sorted by recency.

  • scan_mcp_server

    Run a full security scan of an MCP server. Performs prompt injection detection, credential scanning, endpoint probing, tool poisoning analysis, and blast radius scoring. Args: url: The MCP server URL to scan (e.g. http://localhost:8000). auth_token: Optional Bearer token to authenticate with the server. Returns: Structured security report as a dict, including summary and all findings.

  • scan_tool_definitions

    Analyze MCP tool definitions JSON for prompt injection and poisoning risks. Accepts either a JSON array of tool objects or a single tool object. Args: tool_json: JSON string of tool definitions to analyze. Returns: Dict with injection_findings, tool_risk_profiles, and summary.

Compare and alternatives

    Featured in

    Signals

    Weekly downloads
    183
    Last release
    Jun 4, 2026 (4 months ago)
    Last package publish
    Oct 19, 2026 (12 days ago)

    From the package registry.

    Details

    Registry name
    com.cognivators/mcp-safeguard
    Version
    0.3.2
    Auth
    No auth
    Packages
    pypi mcp-safeguard
    License
    License unknown
    Repository
    gitlab.com/anasmohiuddinsyed/mcp-safeguard
    First seen
    Oct 24, 2026
    Last checked
    Oct 25, 2026
    Source
    Official MCP Registry

    Done for you

    Rather not set it up yourself?

    Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

    See how we build AI agents →Read the case studies

    Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

    launches shipped
    50+
    launches shipped
    media placements
    500+
    media placements
    founders on every account
    2
    founders on every account

    Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

    Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

    Get MCP Safeguard running in your business

    Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

    Goes to the Chalk Labs founders, not the newsletter. Privacy

    Need help deploying MCP Safeguard?

    CallGet help
    Cite this page

    MCP Safeguard. Agent Mart. https://agentmart.dev/connectors/cognivators-com-mcp-safeguard (last updated 2026-10-25)