Agent skill
ragsharp-mcp-code-graph
Run the ragsharp MCP JSON-RPC server and issue graph commands (doctor/index/update/query/export) for Codex/agent integrations. Triggers: mcp, json-rpc, code graph, references, index, query, export.
Install this agent skill to your Project
npx add-skill https://github.com/managedcode/RagSharp/tree/main/assets/skill-templates/mcp-code-graph
SKILL.md
Steps
- Start the MCP server:
ragsharp-mcp(reads stdin, writes stdout). - Send JSON-RPC 2.0 requests, e.g.
{"jsonrpc":"2.0","id":1,"method":"doctor","params":{"root":"."}}. - For indexing:
{"jsonrpc":"2.0","id":2,"method":"index","params":{"root":".","db": ".ragsharp/graph/index.db","state": ".ragsharp/graph/state.json"}}. - For querying:
{"jsonrpc":"2.0","id":3,"method":"query","params":{"db": ".ragsharp/graph/index.db","type":"symbols","symbol":"Greeter","edgeKind":null,"limit":50}}. - For export:
{"jsonrpc":"2.0","id":4,"method":"export","params":{"db": ".ragsharp/graph/index.db","format":"dot","output": ".ragsharp/graph/graph.dot"}}.
Expected Results
- Server responds with JSON-RPC 2.0 responses containing
resultorerror. - Indexing returns counts of nodes/edges and writes
.ragsharp/graph/index.dbandstate.json. - Query returns
nodesandedgesmatching filters (type,symbol,kind,document,edgeKind,limit,contextLines). - Export writes DOT or GEXF to the requested path.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ragsharp-query-code-graph
Query the ragsharp code graph for declarations, references, callers, callees, dependencies, and line-number evidence. Triggers: find usages, where defined, callers, callees, dependency path, project deps, type hierarchy, line numbers, evidence.
ragsharp-build-code-graph
Build or update a code graph index for C#/.NET repositories using ragsharp-graph. Triggers: build index, update index, refresh index, code graph, dependency graph, static analysis, Roslyn, line numbers.
mcaf-architecture-overview
Create or update `docs/Architecture.md` as the global architecture map for a solution. Use when bootstrapping a repo, onboarding, or changing modules, boundaries, or contracts. Keep it navigational and use `references/overview-template.md` for scaffolding.
mcaf-human-review-planning
Plan a human review for a large AI-generated code drop by reading the target area, tracing the natural user and system flows, identifying the riskiest boundaries, and prioritizing the files a human should inspect first. Use when the codebase is too large to review line-by-line and you need a practical review sequence plus a prioritized file list.
mcaf-documentation
Create or refine durable engineering documentation: docs structure, navigation, source-of-truth placement, and writing quality. Use when a repo’s docs are missing, stale, duplicated, or hard to navigate, or when adding new durable engineering guidance.
mcaf-observability
Design or improve observability for application and delivery flows: logs, metrics, traces, correlation, alerts, and operational diagnostics. Use when a change affects runtime visibility, failure diagnosis, SLOs, or alerting.
Didn't find tool you were looking for?