74
/ 100
17 days ago
glama

vkb

A local-first semantic memory system that enables document ingestion, semantic querying, and knowledge graph traversal via MCP.

Is this your MCP?

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.

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
⚠️
Known vulnerabilities in dependencies: 1 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 3 credentials: MCP_SECRET, OBS_SECRET, TLS_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies1 high3 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

highws@8.20.0GHSA-96hv-2xvq-fx4p

ws: Memory exhaustion DoS from tiny fragments and data chunks

lowjs-yaml@4.1.1GHSA-h67p-54hq-rp68

JS-YAML: Quadratic-complexity DoS in merge key handling via repeated aliases

lowuuid@13.0.0GHSA-w5hq-g745-h8pq

uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided

ws: Uninitialized memory disclosure

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configCHUNK_OVERLAP64 Overlap between adjacent chunks
configCHUNK_SIZE512 Target chunk size in tokens
configCHUNK_SUMMARY_PROMPT_FILEPer-chunk summary prompt
configDATABASE_URL"": "postgres://vkb:vkb@localhost:5433/vkb",
configEMBED_DIM768 Embedding dimension (must match model output)
configEMBED_MODEL"": "nomic-embed-text",
configINGEST_MAX_RETRIES3 Max times a failed job is re-queued
configIVFFLAT_LISTS100 Number of ivfflat lists (tune alongside chunk count)
configIVFFLAT_THRESHOLD1000 Chunk count above which an ivfflat index is created/maintained
configJOB_TTL_DAYS7 Days before completed/failed jobs are expired
configLLM_EXTRACT_CANDIDATES20 Candidate chunks the LLM considers per extraction pass
configLLM_MODEL"": "gemma4:e4b",
configLLM_RELATION_EXTRACTIONtrue Use LLM to extract relations (set false to use heuristics only)
configLOG_LEVELinfo Log verbosity: debug, info, warn, error. Pass --debug at startup as a shorthand for LOG_LEVEL=debug — also enables full request/response logging on all HTTP endpoints and MCP tool call tracing
configMCP_PORTvkb uses stdio transport when is 0. The MCP server is also accessible over HTTP Streamable (MCP 2025-03-26 spec) when MCP_PORT > 0 (default 3333), with session management for multi-client use.
🔐 secretMCP_SECRETBearer token for the HTTP MCP endpoint on MCP_PORT (leave unset to disable)
configMCP_STDIO
configOBS_PORTThe observability server runs on (default 4242) and exposes both the SPA and a REST API.
🔐 secretOBS_SECRETSet =your-secret in .env. When set, all API requests must include:
configOLLAMA_BASE_URL"": "http://localhost:11434",
configRAWSTORE_ADAPTERfilesystem Raw content storage: filesystem or s3
configRAWSTORE_PATH./rawstore Root path for filesystem rawstore
configRAWSTORE_S3_BUCKETS3 bucket name (when RAWSTORE_ADAPTER=s3)
configRAWSTORE_S3_ENDPOINTS3-compatible endpoint URL (optional override)
configRELATION_CONFIDENCE_STEP0.05 Increment applied on relation confirmation
configRELATION_EXTRACT_PROMPT_FILERelation extraction prompt
configRELATION_PRUNE_THRESHOLD0.6 Confidence below which relations are pruned on retune
configRELATION_THRESHOLD0.75 Minimum cosine similarity to create a relation
configRELATION_TOP_K10 Nearest neighbours considered per chunk
configRELATION_TTL_DAYS30 Days before unconfirmed relations are pruned
configRETUNE_INTERVAL_HOURS6 How often the retune worker runs automatically (0 = disabled)
configRETUNE_SUMMARISEfalse Regenerate entity summaries during retune
configSECTION_MAX_SIZE8 Max chunks per section
configSECTION_SPLIT_THRESHOLD0.65 Cosine similarity drop that triggers a section boundary
configSECTION_STRATEGYsimilarity_valley Sectioning strategy: similarity_valley or positional
configSECTION_SUMMARY_PROMPT_FILESection summary prompt
configSECTION_WINDOW_SIZE5 Sliding window size for valley detection
configSUMMARY_CONCURRENCY4 Parallel LLM calls during the summarising stage
configSUMMARY_MAX_INPUT_CHARS12000 Max characters fed to the entity-level summary prompt (~3 k tokens)
configSUMMARY_PROMPT_FILEEntity summary prompt
configTLS_CERTPath to TLS certificate file (enables HTTPS/WSS on all servers)
🔐 secretTLS_KEYPath to TLS private key file
configWORKER_CONCURRENCY2 Number of ingest worker processes
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 8 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/inkiebeard-galactic-vkb-c8gpsp)](https://m8ven.ai/mcp/inkiebeard-galactic-vkb-c8gpsp)
commit: 304dfe55c2c4509f983a545935ee085403d78025
code hash: 947726b9f7009605bd9e4d01b45381bc1deb2be3fd64c76865574f2bb4195e69
verified: 6/22/2026, 12:59:25 PM
view raw JSON →