gamecode-rag
Enables semantic search and call-graph exploration over decompiled Unity Mono C# codebases, with hybrid retrieval, LLM re-ranking, and lazy-loaded project indexes.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
rkuhn153
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
list_available_projectsLists game code projects on disk (indexes load into memory only when first searched).
code_search_and_rerankHybrid search (dense embeddings + keyword/symbol) then AI re-rank for the top C# snippets in a project.
code_graph_searchFinds functions that call (upstream) or are called by (downstream) a specific function ID in a *specific project*.
ingest_new_projectAutomates the full RAG ingestion pipeline for a new Mono game. Can decompile a Mono assembly automatically if assembly_path (DLL path or game directory) is provided. Arguments: - project_id: Unique ID for the project (e.g. 'my_game'). - source_code_path: Folder where C# files live, or where decompil…
RE_RANKER_MODELWorks with Ollama, LM Studio, vLLM, TEI, etc. Re-ranker still uses OpenRouter by default (OPENROUTER_API_KEY + ); if the key is missing, search skips re-rank and returns hybrid order.OPENROUTER_API_KEYWorks with Ollama, LM Studio, vLLM, TEI, etc. Re-ranker still uses OpenRouter by default ( + RE_RANKER_MODEL); if the key is missing, search skips re-rank and returns hybrid order.BROAD_SEARCH_KKEYWORD_SEARCH_KEMBEDDING_BACKENDopenai_compatibleEMBEDDING_MODELqwen3-embedding:0.6bEMBEDDING_BASE_URLEMBEDDING_API_KEYTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
4/4 tools missing one or more hints — list_available_projects (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); code_search_and_rerank (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); code_graph_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +1 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Destructive tools are labelled
1 tool perform destructive updates without destructiveHint — ingest_new_project deletes at line 638 (os.remove(os.path.join(root, f)))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Tool inputs are validated
3/4 tool handlers declare input schemas (75%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
3/4 tool handlers wrap calls in try/catch (75%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/rkuhn153/gamecode-rag)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check