vkb (inkiebeard/galactic-vkb) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: we have no way to read this server ourselves. No publisher has claimed this listing.

C
Caution
74/100
2 months ago

vkb

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

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

Code Verified⚡ Live Monitored: not connected

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

inkiebeard

Source: Glama

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. 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.

// 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 →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configCHUNK_OVERLAP64 Overlap between adjacent chunks
configCHUNK_SIZE512 Target chunk size in tokens
configCHUNK_SUMMARY_PROMPT_FILEPer-chunk summary prompt
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
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployDATABASE_URL
// quality suggestions

Tool 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

16/16 tools missing one or more hints — vkb_ingest (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); vkb_ingest_bulk (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); vkb_ingest_okf (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +13 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

14/16 tool handlers declare input schemas (88%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

Only 0/16 tool handlers wrap calls in try/catch (0%)

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.).

Tool test coverage

Only 0/16 tools referenced in tests (0%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

3 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

0 critical, 1 high severity in production deps — ws@8.20.0 (high), js-yaml@4.1.1 (low)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dependency freshness

1/12 production deps stale: umap-js@2024-06-05 (2y)

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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// 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 Verified](https://m8ven.ai/badge/mcp/inkiebeard-galactic-vkb-c8gpsp?variant=verified)](https://m8ven.ai/mcp/inkiebeard-galactic-vkb-c8gpsp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 304dfe55c2c4509f983a545935ee085403d78025
code hash: 947726b9f7009605bd9e4d01b45381bc1deb2be3fd64c76865574f2bb4195e69
verified: 6/22/2026, 12:59:25 PM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client