mcp-cs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCS_MODULES | No | Comma-separated list of tool modules to enable (e.g., algo,doctor). Also configurable via the --modules CLI argument. If not set, all modules are enabled. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| algo_run_sandboxedB | Executes code in an isolated process with strict timeout and memory limits (supports python, javascript, typescript, cpp, c, go) |
| algo_run_dockerA | Executes code inside a zero-trust ephemeral Docker container (python:alpine, node:alpine, gcc:alpine) with no network access |
| algo_stress_testA | Automated differential tester: runs a fast solution against a brute-force baseline using randomized inputs until a failing edge case is found |
| algo_check_plagiarismA | Compares two code submissions using token-level AST analysis and returns similarity percentage and verdict |
| algo_generate_edge_casesB | Generates adversarial corner cases (min N=1, max bounds, identical items, extreme negatives, disconnected graphs) |
| wasm_run_moduleC | Executes pre-compiled WebAssembly (.wasm) binary in memory with exported function calls |
| wasm_run_vm_sandboxA | Executes JavaScript in an isolated Node.js VM context with strict execution timeout and zero filesystem access |
| db_generate_erdA | Parses SQL table definitions and generates a clean Mermaid Entity-Relationship (ER) Diagram |
| perf_audit_assetsA | Scans repository for oversized raster images (>250KB) and calculates bandwidth savings from WebP/AVIF conversion |
| perf_check_headersA | Audits HTTP response headers of a web application for Gzip/Brotli compression, Cache-Control, and security headers |
| doctor_diagnose_projectA | Scans project structure, detects language/framework, missing dependencies, and setup issues |
| doctor_check_envA | Compares .env against .env.example and flags missing or extra environment keys |
| doctor_port_inspectA | Checks if specific network ports (e.g. 3000, 6379, 5432) are occupied and by which process PID |
| security_scan_secretsA | Scans repository text files for accidentally hardcoded API keys, JWTs, and private tokens |
| security_auto_sanitizeA | Auto-replaces detected hardcoded secrets with process.env references and populates .env.example |
| api_test_requestC | Executes an HTTP request (GET, POST, PUT, DELETE, PATCH) and measures latency & formats response data |
| api_generate_mock_dataC | Generates realistic synthetic mock data (users, products, posts, transactions) for testing |
| docs_check_broken_linksA | Scans all markdown files (.md, .mdx) in the project to detect broken internal links and dead file references |
| docs_auto_fix_linksB | Automatically updates and rewrites broken markdown links when target files have moved |
| docs_extract_code_snippetsB | Extracts all fenced code blocks from markdown documentation for quick inspection and review |
| code_find_todosA | Scans the codebase for TODO, FIXME, HACK, and BUG comments with line numbers and file paths |
| code_inspect_heavy_dependenciesA | Inspects package.json to identify bloated dependencies (moment, lodash, monaco, katex) with optimization tips |
| git_generate_changelogA | Parses conventional git commit history between tags and outputs a clean markdown changelog |
| git_pr_readiness_checkA | Verifies uncommitted files, unpushed commits, and branch health before opening a Pull Request |
| git_generate_pr_descriptionA | Generates a structured markdown Pull Request description summarizing branch commits and diffs |
| problem_fetch_codeforcesA | Fetches problem statement metadata, tags, and contest limits from Codeforces |
| skills_installA | Installs official MCS agent skills (algo-stress-testing, repo-doctor, db-architect, security-auditor) into local repository (.agents/skills/ or .cursor/rules/) |
| ci_generate_workflowB | Generates production-ready GitHub Actions CI/CD workflows for Next.js, NPM Publishing, Docker, or Python |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| diagnose-repo | Runs a complete system doctor diagnostic, checks environment variables, scans ports, and generates an onboarding report |
| stress-test-solution | Interactive prompt to test a fast algorithm against a brute-force baseline on randomized test inputs |
| prepare-pr | Runs pre-flight PR checks, detects uncommitted files, generates release changelogs, and drafts a PR description |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Active Network Ports | Live snapshot of common development ports (3000, 6379, 5432, 8000, 8080) |
| Git Repository Status | Current git branch, uncommitted files, and upstream sync state |
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/ieeecsopen/mcp-cs'
If you have feedback or need assistance with the MCP directory API, please join our Discord server