deep-code-security
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DCS_MAX_FILES | No | Max files per scan. | 10000 |
| DCS_FUZZ_MODEL | No | Claude model for input generation. | claude-sonnet-4-6 |
| DCS_MAX_RESULTS | No | Max findings returned per hunt operation. | 100 |
| DCS_FUZZ_CONSENT | No | Pre-configured consent for CI. | false |
| ANTHROPIC_API_KEY | No | API key for Claude (required for fuzzing). | |
| DCS_ALLOWED_PATHS | No | Comma-separated list of allowed project paths. | |
| DCS_QUERY_TIMEOUT | No | Tree-sitter query timeout in seconds. | 5.0 |
| DCS_REGISTRY_PATH | No | Path to deep-code-security registries directory. | |
| DCS_FUZZ_GCP_REGION | No | GCP region for Vertex AI. | us-east5 |
| DCS_FUZZ_OUTPUT_DIR | No | Corpus and report output directory. | ./fuzzy-output |
| DCS_FUZZ_TIMEOUT_MS | No | Per-input execution timeout in milliseconds. | 5000 |
| DCS_SANDBOX_TIMEOUT | No | Per-exploit timeout in seconds. | 30 |
| DCS_SCANNER_BACKEND | No | Scanner backend: semgrep, treesitter, or auto. | auto |
| DCS_SEMGREP_TIMEOUT | No | Maximum seconds for Semgrep subprocess. | 120 |
| DCS_FUZZ_MCP_TIMEOUT | No | Hard wall-clock timeout for MCP fuzz invocations. | 120 |
| GOOGLE_CLOUD_PROJECT | No | GCP project ID for Vertex AI (optional). | |
| DCS_CONTAINER_RUNTIME | No | Container runtime: docker, podman, or auto. | auto |
| DCS_FUZZ_MAX_COST_USD | No | API cost budget in USD. | 5.0 |
| DCS_MAX_VERIFICATIONS | No | Max findings to verify in auditor phase. | 50 |
| DCS_QUERY_MAX_RESULTS | No | Max results per tree-sitter query. | 1000 |
| DCS_BRIDGE_MAX_TARGETS | No | Max fuzz targets produced by SAST-to-Fuzz bridge. | 10 |
| DCS_SEMGREP_RULES_PATH | No | Path to DCS Semgrep rule files. | |
| CLOUD_ML_PROJECT_NUMBER | No | GCP project number for Vertex AI (optional). | |
| DCS_FUZZ_MAX_ITERATIONS | No | Max fuzzing iterations. | 10 |
| DCS_FUZZ_ALLOWED_PLUGINS | No | Comma-separated allowlist of fuzzer plugins (python, c). | python |
| DCS_FUZZ_CONTAINER_IMAGE | No | Podman image for Python fuzz container. | dcs-fuzz-python:latest |
| DCS_FUZZ_C_COMPILE_FLAGS | No | Comma-separated gcc flags for C harness compilation. | |
| DCS_FUZZ_C_INCLUDE_PATHS | No | Comma-separated include paths for C harness compilation. | |
| DCS_FUZZ_INPUTS_PER_ITER | No | Inputs generated per iteration. | 10 |
| DCS_FUZZ_C_CONTAINER_IMAGE | No | Podman image for C fuzz container. | dcs-fuzz-c:latest |
| ANTHROPIC_VERTEX_PROJECT_ID | No | Vertex AI project override (optional). | |
| DCS_MAX_CONCURRENT_SANDBOXES | No | Concurrency limit for sandbox execution. | 2 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/backspace-shmackspace/deep-code-security'
If you have feedback or need assistance with the MCP directory API, please join our Discord server