{"data":{"slug":"glitterkill-sdl-mcp","name":"sdl-mcp","tagline":"A policy-centered context budget layer for coding agents that enhances code analysis and workflow efficiency.","github_url":"https://github.com/GlitterKill/sdl-mcp","owner":"GlitterKill","repo":"sdl-mcp","owner_avatar_url":"https://avatars.githubusercontent.com/u/88055815?v=4","primary_language":"TypeScript","stars":417,"forks":25,"topics":["agent-context","agent-tools","agentic-coding","agentic-engineering","agentic-workflow","code-analysis","code-context","code-graph","codegraph","coding-agent","context-budget","context-engine","mcp","polyglot","semantic-analysis","token-savings","tree-sitter","vector-database","vector-search","vibe-coding"],"archived":false,"github_pushed_at":"2026-07-11T00:25:54+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/glitterkill-sdl-mcp","markdown_url":"https://www.graphcanon.com/tools/glitterkill-sdl-mcp.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/glitterkill-sdl-mcp","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=glitterkill-sdl-mcp","description":"Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools.  It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.","homepage_url":null,"license":"Other","open_issues":2,"watchers":5,"ai_summary":"SDL-MCP (Symbol Delta Ledger) is a tool focused on improving the performance of AI-driven coding tasks by managing and optimizing codebase contexts. It employs technologies like semantic analysis, vector databases, and tree-sitter to streamline workflows and improve agent output in agentic engineering environments.","readme_excerpt":null,"github_created_at":"2026-02-08T20:34:49+00:00","created_at":"2026-07-11T11:35:33.572172+00:00","updated_at":"2026-07-12T05:58:22.976259+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"semantic-analysis","name":"semantic-analysis"},{"slug":"agent-tools","name":"agent-tools"},{"slug":"agentic-engineering","name":"agentic-engineering"},{"slug":"agent-context","name":"agent-context"},{"slug":"code-graph","name":"code-graph"},{"slug":"agentic-coding","name":"agentic-coding"},{"slug":"context-budget","name":"context-budget"},{"slug":"code-analysis","name":"code-analysis"}],"trust":{"provenance":{"is_fork":false,"github_id":1153052331,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T11:35:34.242Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":null,"days_since_push":0,"last_release_at":null},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:35:34.833Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"mcp":{"source":"package.json:@modelcontextprotocol/*","observed_at":"2026-07-12T05:57:57.262Z","server_manifest":true},"scan":{"source":"repo_scan","observed_at":"2026-07-12T05:57:57.262Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-07-12T05:57:57.262Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-07-12T05:57:57.262Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-07-12T05:57:57.262Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When working with sprawling or complex codebases where maintaining context across multiple files is crucial.","For projects that require significant token savings since SDL-MCP aims to optimize the use of tokens (potentially reducing costs in pay-per-token models).","If semantic analysis and precise vector database integration are critical, enhancing the quality of AI-driven code suggestions and analysis."],"when_not_to_use":["In environments where TypeScript is not a preferred or supported language.","For tasks that do not benefit from context management layers, such as small-scale projects with straightforward workflows.","If your project requires real-time response times for every operation since SDL-MCP's focus on semantic analysis and context budgeting can introduce slight delays."],"source":"enrich:decision_facts","observed_at":"2026-07-12T05:58:22.752Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"SDL-MCP is a policy-centered tool designed specifically to improve AI-driven coding tasks by managing contexts more efficiently through technologies such as semantic analysis and tree-sitter."}]}}