AI capabilities
What is MCP Server?
Exposing the tool's capabilities over Model Context Protocol so AI agents can call it directly.
MCP is an open protocol that lets an AI agent discover and invoke external tools. A vendor shipping an MCP server means an agent can request a scan, read findings and act on them as part of its own loop, without a bespoke integration.
In practice this is how a scanner becomes part of an agentic workflow rather than a downstream gate, since the agent checks its work before proposing it, instead of a human discovering the problem two steps later.
Top 18 MCP Server tools
Every tool in the directory documented as supporting MCP Server, 13 fully, 5 partially, with what its own documentation says.
Support is not the same as parity, since some implementations are narrower in scope, gated to a higher plan tier, or maintained only for existing customers. The note under each tool is what its own documentation describes.
- 1CodacyQuality Platform
MCP integration for Copilot, Cursor, Windsurf, Claude Code and Claude.ai; included free.
- 2
Aikido MCP Plugin exposes its own MCP server (scan, list/ignore issues, login tools) for AI agents
- 3Checkmarx OneCode Security Platform
Checkmarx Developer Assist is delivered as an agentic MCP server for IDE-based AI assistants.
- 4CodeAnt AIPR Review
MCP Server integration listed for AI-assisted workflows; no tool list or transport documented
- 5CodeSceneQuality Platform
CodeHealth MCP server executes locally on-machine, exposes code_health_review and a review-plan-refactor-remeasure loop
- 6CorgeaCode Security Platform
Corgea exposes its own MCP server: 9 read-only tools for scans, issues, dependencies, blocking rules
- 7DeepSourceQuality Platform
mcp.deepsource.com with 30 tools, OAuth and PAT auth; optional admin toggle on Enterprise Server v5.1.0+.
- 8GitHub Advanced SecurityCode Security PlatformMCP server free; security toolsets require GHAS add-on
Official GitHub-maintained MCP server exposes code_security, secret_protection, dependabot toolsets; code scanning needs GHAS
- 9GreptilePR Review
Hosted MCP server at api.greptile.com/mcp, API-key authenticated, exposing 11 tools
- 10QodoPR Review
Context Engine MCP exposes deep_research, context_ask, get_context; local and remote MCPs in IDE
- 11SemgrepCode Security Platform
Guardian MCP server; Claude Code uses Semgrep's hosted remote server via OAuth with a fixed ruleset.
- 12SnykCode Security Platform
Local MCP server runs the Snyk CLI with scan tools; no hosted or remote MCP server offered.
- 13SonarQubeQuality Platform
SonarQube MCP Server for agent context; Vortex MCP integration tied to Sonar Agent Essentials.
- 14
Codex consumes MCP servers (e.g. Linear); no MCP server exposing review or scan findings documented.
- 15
Consumes MCP servers with first-use trust verification; no MCP server exposing review findings documented.
- 16
Acts as MCP client consuming external servers (Pro 5, Pro+ 15, Enterprise 20); exposes none
- 17
Bugbot consumes configured MCP servers; no MCP server exposing findings. Team and Enterprise only.
- 18
Agent Mode and Gemini CLI consume local and remote MCP servers; no MCP server exposing review findings.
What to look for
- Which operations the server exposes, such as read-only findings, or scan and remediate
- Which agent clients are known to work with it
- Authentication model and what scope the agent's token carries
- Whether MCP access is included in your plan tier
Related terms
FAQ
What is MCP Server?
Exposing the tool's capabilities over Model Context Protocol so AI agents can call it directly.
How many tools support MCP Server?
18 of the 20 tools tracked in this directory support MCP Server, 13 fully and 5 partially, including Codacy, Aikido, Checkmarx One, CodeAnt AI, CodeScene. Support is not the same as parity, since some implementations are narrower in scope, gated to a higher plan tier, or maintained only for existing customers. The note under each tool is what its own documentation describes.
What should you look for in MCP Server?
Which operations the server exposes, such as read-only findings, or scan and remediate. Which agent clients are known to work with it. Authentication model and what scope the agent's token carries. Whether MCP access is included in your plan tier.