Skip to content
MCP server

Sphior Code MCP

Local deterministic security scan of your workspace with fix guidance for your AI agent

Runs locallyStatus and history
Pricing
Freemium
Platforms
CLI, self-hosted
Runs
Locally
Version
1.1.13
Listing updated
3 days ago

About Sphior Code MCP

Sphior Code MCP is a freemium MCP server for security. It runs locally on your machine and is started by your AI client.

The engine behind this package is rule-based rather than model-based: it scans the workspace in local mode with no account and hands findings, plus how to fix them, to the assistant. Tools named in the README include get_fix_context and health_check.

Adding a SPHIOR_API_KEY extends it to repositories connected to SPHIOR on GitHub, with scan history and verifiable records. Optional variables set the directory to scan, the API base for self-hosted or regional deployments and a timeout between 1 and 300 seconds.

The wider SPHIOR CODE product scans pull requests through a GitHub App for SQL injection, cross-site scripting, hard-coded secrets and vulnerable dependencies, and says analysis happens in memory with source never stored. Its code scanning plan starts at $79 a month.

Install

Run in a terminal

claude mcp add sphior-code-mcp --env SPHIOR_API_KEY='<SPHIOR_API_KEY>' -- npx -y sphior-code-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "sphior-code-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "sphior-code-mcp"
      ],
      "env": {
        "SPHIOR_API_KEY": "<SPHIOR_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "sphior-code-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "sphior-code-mcp"
      ],
      "env": {
        "SPHIOR_API_KEY": "<SPHIOR_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "sphior-code-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "sphior-code-mcp"
      ],
      "env": {
        "SPHIOR_API_KEY": "<SPHIOR_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "sphior-code-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "sphior-code-mcp"
      ],
      "env": {
        "SPHIOR_API_KEY": "<SPHIOR_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "sphior-code-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "sphior-code-mcp"
      ],
      "env": {
        "SPHIOR_API_KEY": "<SPHIOR_API_KEY>"
      }
    }
  }
}

Configuration

  • SPHIOR_API_KEYOptional. Without it the server runs in local mode: it scans your workspace with the bundled deterministic engine and returns fix guidance. Set it to also reach the repositories you connected to SPHIOR on GitHub, with their history and verifiable scan records. Create one under Settings → API at https://sphior.com/app?settings=api
  • SPHIOR_WORKSPACEOptional. Directory to scan in local mode. Defaults to the directory your client launches the server in.
  • SPHIOR_API_BASEOverride the API base URL for self-hosted / regional deployments. Default: https://sphior.com/api/v1
  • SPHIOR_TIMEOUTOptional. Local scan and request timeout in milliseconds (1000–300000). Default: 30000

Tools this server provides (2)

Taken from the project documentation; the running server may differ.

get_fix_context
Returns fix guidance for a finding.
health_check
Checks the server and connection.

What it does

Local scanning
Scans your workspace with a bundled deterministic engine.
Fix guidance
get_fix_context returns what an agent needs to repair a finding.
No account to start
Works without an API key.
Connected repositories
With a key, reach GitHub repos with history and scan records.
Configurable
Set workspace, API base and timeout through environment variables.

Good for

  • Check code for injection or hard-coded secrets before committing
  • Ask an agent to fix a finding using given context
  • Review a connected repository's scan history
  • Verify the scanner is reachable with a health check

Pricing

Freemium, from $79 a month

Local mode free; SPHIOR CODE scanning from $79/mo (Team plan)

Prices change. Check sphior.com before you buy.

Sphior Code MCP FAQ

Do I need an account?

No; without a key it runs in local mode.

What does an API key add?

Access to repositories connected on GitHub, with history and verifiable scan records.

Does it use AI to find issues?

The product describes its engine as deterministic, with no AI.

Is Sphior Code MCP free?

Sphior Code MCP has a free plan, with paid plans for more usage or features. Paid plans start at $79 a month.

How do I add Sphior Code MCP to Claude Code?

Run this command in your terminal: claude mcp add sphior-code-mcp --env SPHIOR_API_KEY='<SPHIOR_API_KEY>' -- npx -y sphior-code-mcp

What are the best alternatives to Sphior Code MCP?

The closest alternatives to Sphior Code MCP are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Sphior Code MCP

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools