mcpField
S
Sekura

Sekura

Remote
sekura.aiSecurity0Updated 1w ago

About Sekura

Sekura provides an MCP server and manifests for connecting coding agents to GitHub repository vulnerability scans. Agents can inspect repositories, initiate approved scans, review findings with proof, and manage schedules.

Key features

  1. 01GitHub repository vulnerability scans
  2. 02Evidence for each finding
  3. 03Repository listing and findings access
  4. 04Approved scan initiation
  5. 05Recurring scan schedule management
  6. 06OAuth 2.1 sign-in

Use cases

  1. 01Inspect reported vulnerabilities in a GitHub repository
  2. 02Start a scan after reviewing its preview
  3. 03Review findings and manage recurring scans

MCP support

The manifests connect clients to the hosted Sekura MCP server at https://sekura.ai/mcp. Read tools need no confirmation; write operations first return a preview and run only after approval.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://sekura.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Sekura plugins

Manifests that connect AI coding tools to the Sekura MCP server at https://sekura.ai/mcp.

Sekura scans a GitHub repository for vulnerabilities and delivers a report with proof for every finding; from your agent you can see your repositories, start a scan you have approved, read the findings, and manage a schedule.

This repository holds manifests only. Every one of them points at the same server, and nothing here runs on your machine: sign-in is OAuth 2.1 at the server (PKCE, Dynamic Client Registration, Client ID Metadata Documents), so no key is copied anywhere. The full guide for every tool, with the exact snippet or one-click link, is at https://sekura.ai/connect/.

Install

ToolHow
Claude Code/plugin marketplace add sekuraai/sekura-plugins, then /plugin install sekura@sekura. Or without the plugin: claude mcp add --transport http sekura https://sekura.ai/mcp then /mcp to sign in
Claude (app and web)Settings, Connectors, Add custom connector, address https://sekura.ai/mcp
CursorThe one-click link on https://sekura.ai/connect/, or clone this repository into ~/.cursor/plugins/local/ (the plugin is this repository's root)
KiroAdd Custom Power, Import power from GitHub, this repository
Antigravityantigravity/: the manifest and mcp_config.json; or add https://sekura.ai/mcp as a custom server
VS Code, Copilot CLI, JetBrains, Zed, Codex, Devin, Replit, Lovable, Bolt, v0 and the resthttps://sekura.ai/connect/

What is where

PathVenue
.claude-plugin/marketplace.json, plugins/sekura/Claude Code plugin marketplace; the plugin's skill teaches the quote-then-confirm flow
plugin.json, mcp.jsonAgent Plugins standard manifest at the root: Kiro Powers, Cursor
.cursor-plugin/plugin.jsonCursor Marketplace and cursor.directory
registry/server.jsonThe official MCP Registry entry, ai.sekura/sekura, published with mcp-publisher
docker/servers/sekura/The Docker MCP Catalog entry, submitted as a pull request to docker/mcp-registry
cline/The Cline marketplace listing: README, llms-install.md, 400 by 400 logo
antigravity/Google Antigravity plugin manifest and MCP configuration
gemini/gemini-extension.jsonGemini CLI extension (legacy gallery)
logo.pngThe Sekura owl, 512 by 512

How the server behaves

Read tools are free and need no confirmation. Every write tool (start a scan, start a recurring plan, run a plan now, cancel) answers first with a preview that names the repository, the authorization wording and the price, and runs only when called again with the arguments the preview names, after the user has agreed in the conversation. A card is charged only after the user approves the quoted amount; otherwise the answer carries a Stripe Checkout link.

Privacy: https://sekura.ai/privacy/. Terms: https://sekura.ai/terms/. Support: [email protected].

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.