semgrep/mcp
📇 ☁️ Allow AI agents to scan code for security vulnerabilites using [Semgrep](https://semgrep.dev).
Ads
Overview
📇 ☁️ Allow AI agents to scan code for security vulnerabilites using [Semgrep](https://semgrep.dev).
Installation
uvx semgrep-mcp # see --help for more options
Configuration
{
"mcpServers": {
"semgrep": {
"command": "uvx",
"args": ["semgrep-mcp"],
"env": {
"SEMGREP_APP_TOKEN": "<token>"
}
}Capabilities
- Scan code for security vulnerabilities
Ask the assistant to run `security_check` or `semgrep_scan` on a code snippet or file to find security issues.
- Scan with a custom Semgrep rule
Use `semgrep_scan_with_custom_rule` to check code against a rule you provide inline.
- Fetch findings from Semgrep AppSec Platform
Retrieve existing project findings via `semgrep_findings` when a Semgrep token is configured.
- Inspect code structure
Get the Abstract Syntax Tree of a code snippet with `get_abstract_syntax_tree` to understand its parsed structure.
- Get help writing a custom rule
Use the `write_custom_semgrep_rule` prompt to generate a template for a new Semgrep rule.
Tags
- security
- code-quality
- development
- devops
- awesome-list
Related MCP servers
laszlopere/mcp-bytesmith
Local byte-wrangling toolbox: encoding (hex/Base64/Base32/Base58/Base45…), cryptographic + CRC hashing, base conversion, and CSPRNG tokens/passphrases, plus an opt-in Ethereum/EVM toolset (keccak, ABI/RLP codecs, EIP-191/712 hashing, function/event selectors, EIP-55). No network calls. `uvx mcp-bytesmith`.
degenlegion-com/waxseal-sdk
On-chain Ed25519 identity for AI agents — verify seals by fingerprint, validate document signatures, and gate irreversible actions behind human-signed approval tokens. Hosted at `api.waxseal.id/mcp`; local install (`npx @waxseal/mcp`) for signing.
tponscr-debug/oracle-h-mcp
Mandatory human approval gate for autonomous AI agents. Intercepts critical, irreversible, or financially significant actions and routes them to a human via Telegram for real-time approve/reject. Raises workflow success probability from 81.5% to 99.6%.
arthurpanhku/DocSentinel
MCP server for AI agent for cybersecurity: automate assessment of documents, questionnaires & reports. Multi-format parsing, RAG knowledge base,Risks, compliance gaps, remediations.