Paparats MCP
Provides AI coding assistants with deep, semantic understanding of local codebases via AST-aware chunking, cross-repo symbol graphs, and architectural memory, enabling context-aware code search and dependency tracing.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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
IBazylchuk
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
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
CHANGE_DETECTIONCONFIG_DIRCRONCRON_FASTEDITORpaparats edit composeprojects Open the file in $; on save, validate +EMBEDDING_MODELOverrides: (defaults: text-embedding-3-small,GITHUB_TOKENCI (auto) Open/update the chore: release PROLLAMA_BATCH_CHARSOLLAMA_BATCH_SIZEOLLAMA_URLOTEL_EXPORTER_OTLP_ENDPOINTunset OTLP HTTP endpoint (e.g. http://localhost:4318/v1/traces)OTEL_EXPORTER_OTLP_HEADERSAuthorization=Bearer <apm-secret-token>OTEL_RESOURCE_ATTRIBUTESunset Extra resource attrs (key=value,key2=value2)OTEL_SERVICE_NAMEpaparats-mcpPAPARATS_ANALYTICS_DB_PATH~/.paparats/analytics.db Analytics DB filePAPARATS_ANALYTICS_ENABLEDtrue Local SQLite analytics writesPAPARATS_ANALYTICS_RETENTION_DAYS90 Daily prune cutoffPAPARATS_ANALYTICS_RETENTION_RUN_HOUR3 Hour-of-day for prune (local time)PAPARATS_GROUPPAPARATS_IDENTITY_HEADERX-Paparats-User Header name for user attributionPAPARATS_INDEXER_URLPAPARATS_LOG_QUERY_TEXTtrue If false, store NULL for search_events.query_textPAPARATS_LOG_RESULT_FILEStrue If false, store NULL for search_results.filePAPARATS_METRICSObservability built in. When =true, every read/write hits aPAPARATS_OTEL_ENABLEDfalse Enable OTel SDK + OTLP exporterPAPARATS_PROJECTSPAPARATS_REFORMULATION_WINDOW_MS90000 Reformulation detection windowPAPARATS_SERVER_URLPAPARATS_TELEMETRY_SAMPLE_RATE1.0 Sampling rate (errors are always kept)PAPARATS_UI_BASIC_AUTHProtect it (optional): =user:pass — applies to /ui and /api/analytics only; /mcp and /api/search stay open so agents keep working.PAPARATS_UI_DEMOShow the screenshot view to anyone without touching real data: =true (or append ?demo=1 to the URL once).QDRANT_API_KEYAsks for an API key after; stored in ~/.paparats/.env as .QDRANT_URLQUERY_CACHE_MAX_ENTRIESmax cached queries (default: 1000)QUERY_CACHE_TTL_MSTTL in milliseconds (default: 300000)REPOSREPOS_DIRSTATE_DB_PATHVISUALPORTTool 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
24/24 tools missing one or more hints — search_code (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); health_check (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_chunk (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +21 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.
Tool inputs are validated
19/24 tool handlers declare input schemas (79%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
12/24 tool handlers wrap calls in try/catch (50%)
Wrap each tool handler body in try/catch and return a structured error response.
Tool test coverage
Only 0/24 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
9 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
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/ibazylchuk/paparats-mcp)?variant=verified to the badge 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