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 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- 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