Skip to content
Agentmart
Submit a tool

Shadowgate MCP

Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.

Connector by josephibra · GitHub account verified by the MCP Registry

IndexedMITRemote (HTTP)
Write a review

Install

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

npx agentmarket install connector/josephibra-shadowgate-mcp

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.

Remote endpoint

  • https://shadowgate-mcp.mcp.xpay.sh/mcp Remote (HTTP)

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

Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.

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 and install config. Checked Oct 25, 2026.

Tools
20 read · 5 write · 0 delete · 1 not yet classified
Secrets
None asked for
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 26

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

Read 20 · Look things up without changing anything.

  • analyze_text
  • decide_policy
  • evaluate_mcp_transaction
  • get_audit_summary
  • get_data_paths
  • get_mcp_server_trust
  • get_policy
  • get_recent_audit_events
  • get_risk_score
  • get_security_config
  • get_server_registry
  • health_check
Show 8 more tools
  • inspect_mcp_response
  • inspect_mcp_tool_call
  • inspect_tool_schema
  • redact_secrets
  • review_mcp_manifest
  • scan_batch
  • scan_text
  • simulate_policy_modes

Write 5 · Create, change, send or run things.

  • approve_mcp_manifest_identity
  • create_security_report
  • gate_mcp_tool_call
  • set_mcp_server_trust
  • set_policy_mode

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

  • gate_mcp_response

Network hosts it talks to 1

  • shadowgate-mcp.mcp.xpay.sh · found in remote endpoint, install command

Tools (26)

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

  • analyze_text

    Professional public text-analysis tool. This merges the practical outputs of: - scan_text - redact_secrets - get_risk_score - decide_policy - simulate_policy_modes Use this as the main public text safety tool.

  • approve_mcp_manifest_identity

    Admin tool to approve and persist a manifest trust identity baseline.

  • create_security_report

    Create a compact security report from recent audit events.

  • decide_policy

    Return the policy decision for a payload: allow, redact, or block.

  • evaluate_mcp_transaction

    Evaluate both sides of an MCP interaction: 1. outgoing tool call arguments 2. incoming MCP response

  • gate_mcp_response

    Gateway decision for an MCP response.

  • gate_mcp_tool_call

    Gateway decision for an outgoing MCP tool call.

  • get_audit_summary

    Return a summary of ShadowGate audit decisions, actions, categories, and severities.

  • get_data_paths

    Return ShadowGate data directory paths for policy, registry, and audit logs.

  • get_mcp_server_trust

    Return trust status for a specific MCP server.

  • get_policy

    Return the active ShadowGate policy configuration.

  • get_recent_audit_events

    Return recent ShadowGate audit events. Raw scanned text is never stored.

  • get_risk_score

    Return a 0-100 risk score for a text payload.

  • get_security_config

    Return ShadowGate admin-auth security configuration without exposing the raw key.

  • get_server_registry

    Return the ShadowGate MCP server trust registry.

Show 11 more tools
  • health_check

    Return ShadowGate MCP health, version, and active policy.

  • inspect_mcp_response

    Scan a response returned by another MCP server before the agent trusts it.

  • inspect_mcp_tool_call

    Scan an outgoing MCP tool call before execution.

  • inspect_tool_schema

    Scan an MCP tool schema/description before allowing agents to use it.

  • redact_secrets

    Return the text with detected secrets and sensitive path snippets redacted.

  • review_mcp_manifest

    Review a simplified MCP server manifest. This is now protected by client_key when SHADOWGATE_CLIENT_KEY is set.

  • scan_batch

    Scan multiple text items in one call. This is now protected by client_key when SHADOWGATE_CLIENT_KEY is set.

  • scan_text

    Scan arbitrary text for leaked secrets, prompt injection, risky commands, and sensitive file paths.

  • set_mcp_server_trust

    Set trust level for an MCP server. Allowed trust levels: - trusted - untrusted - monitor - blocked

  • set_policy_mode

    Change ShadowGate policy mode: monitor, balanced, or strict.

  • simulate_policy_modes

    Show how the same text would be handled under monitor, balanced, and strict modes.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
May 13, 2026 (5 months ago)
Last release
May 14, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.josephibra/shadowgate-mcp
Version
1.0.0
Auth
Auth not stated
License
MIT
Repository
github.com/josephibra/shadowgate-mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from josephibra

Cite this page

Shadowgate MCP. Agent Mart. https://agentmart.dev/connectors/josephibra-shadowgate-mcp (last updated 2026-10-24)