power-framework (weby-homelab/power-framework) is an MCP server listed on the M8ven Trust Index. It scores 32 out of 100, grade F. It declares 21 tools. No publisher has claimed this listing.

F
Warning
32/100

power-framework

Validate, index, search, and manage your knowledge base from the command line — or let AI agents do it through MCP. Built for knowledge workers who want machine-readable notes, automated quality checks, and token-efficient AI access to their Second Brain

Warning. Serious findings were identified. Review the full report before connecting. 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

weby-homelab

Source: github_repo_search

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

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.

// key findings
🚨
Reads files from sensitive locations
Touches: /etc/power/infra/credentials
🚨
Code appears obfuscated
1 file are unreadable to a human reviewer. Cannot audit what they do.
🔐
You'll be asked for 2 credentials: POWER_LLM_API_KEY, OPENROUTER_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes21 tools

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.

get_server_info

Return the versioned read-only runtime and vault discovery report.

lint_vault

Run the P.O.W.E.R. health check / linter to verify note metadata, link integrity, and check for orphans.

generate_index

Compile the vault hierarchical index: a summary index.md plus per-folder _index.md files.

sync_vault

Publish an atomic search-index generation for the configured vault.

read_sub_index

Read one bounded page of a P.A.R.A. sub-index without generating files.

ensure_sub_index

Generate and read one bounded page of a P.A.R.A. sub-index.

ingest_note

Create a new note with strict OKF metadata frontmatter, regenerate the index, and log the change.

get_memory_context

Read transactional-memory context without changing vault state.

propose_memory_change

Persist a reviewable, content-addressed memory proposal without applying it.

apply_memory_change

Apply only an explicitly approved memory proposal.

validate_memory_state

Validate the vault after a transactional-memory operation.

read_memory_history

Read append-only transaction receipts without note content.

handoff_work

Create/read/advance a canonical Task v2; never execute its next action.

infra_action

Call only the configured local INFRA-1 broker; never execute shell text.

search_vault_tool

Search vault notes and return provenance-bearing untrusted data only.

synthesize_session

Create a new session synthesis note with auto-classified OKF frontmatter, Graph RAG related links, and full index/log maintenance.

rot_audit

Run the P.O.W.E.R. ROT audit with local analysis by default.

archive_notes

Move stale/expired notes to 04_Archive. Use dry_run=True (default) to preview first.

suggest_related_tool

Suggest related notes. ``method`` is 'semantic' (dense cosine over BGE-M3) or 'keyword' (legacy Jaccard overlap). Semantic degrades to keyword with a warning when the embedding backend is unavailable.

heal_frontmatter_tool

Scan and heal missing/invalid frontmatter fields across vault notes. Use dry_run=True (default) to preview first.

check_markdown_tool

Check markdown quality issues across the vault: trailing whitespace, list markers, header jumps, code language.

// 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.
configPOWER_BENCHMARK_RECEIPT
configPOWER_VAULT_DIR
configPOWER_EGRESS_POLICY
configGITHUB_REPOSITORY
configGITHUB_SHA
configGITHUB_RUN_ATTEMPT
configGITHUB_EVENT_NAME
configGITHUB_REF
configGITHUB_REF_PROTECTED
configGITHUB_WORKFLOW
configGITHUB_RUN_ID
configSOURCE_DATE_EPOCH
configHF_HOME
configKEEP_PROFILE_CONTAINER
configACCEPTANCE_HARNESS_REVISION
configPOWER_DOMAIN_CONFIG
configPOWER_UPGRADE_VAULT
configPOWER_UPGRADE_MARKER
configPOWER_UPGRADE_POINT
configXDG_CACHE_HOME
configPOWER_FTS_OPERATOR
configPOWER_SEARCH_DB
configPOWER_EMBED_DEVICE
configPOWER_EMBED_NUM_THREADS
configPOWER_RERANKER_DEVICE
configPOWER_RERANKER_BATCH_SIZE
configPOWER_BGE_RERANKER_MAX_TOKENS
configPOWER_EMBED_PROVIDEROptional dense embedding manager: BGE-M3 (default, 1024d, direct ONNX Runtime — BGEM3OnnxManager) / Qwen3-0.6B / MiniLM-L12-v2 (light) via POWER_EMBED_PROVIDER, loaded only on dense paths
configPOWER_SYNC_VMEM_LIMIT_MB
configHF_HUB_CACHE
configPOWER_MODEL_OFFLINE
configHF_HUB_OFFLINE
configHF_HUB_DISABLE_TELEMETRY
configPOWER_LLM_ALLOWED_ORIGINS
configPOWER_EMBED_BATCH_SIZE
configPOWER_EMBED_COMMIT_EVERY
configPOWER_INFRA_SOCKET
configPOWER_INFRA_RUNTIME_DIR
configRUNTIME_DIRECTORY
configCREDENTIALS_DIRECTORY
configLISTEN_PID
configLISTEN_FDS
configPOWER_INFRA_ALLOWED_UIDS
configPOWER_INFRA_ALLOWED_GIDS
configHF_ENDPOINT
configPOWER_ALLOW_DENSE_FALLBACK
configPOWER_COLBERT_MIN_RAM_GB
configPOWER_COLBERT_MODEL
configPOWER_RERANKERThe default BGE reranker is an Apache-2.0 ONNX snapshot with SHA-256 checks. Local jinaai/jina-reranker-v2-base-multilingual is CC-BY-NC-4.0 and requires POWER_RERANKER=jina plus POWER_ALLOW_NONCOMMERCIAL_MODELS=1 for permitted non-commercial use.
configPOWER_OLLAMA_EMBED_MODEL
configPOWER_QWEN3_EMBED_MODEL
configPOWER_BGE_M3_ONNX_REPO
configPOWER_BGE_M3_ONNX_REVISION
configPOWER_EMBED_DEVICE_ID
configPOWER_EMBEDDING_MODEL
configOLLAMA_HOST
configPOWER_OLLAMA_EMBED_TIMEOUT
configPOWER_OLLAMA_EMBED_RETRIES
configPOWER_OLLAMA_THREADS
configPOWER_BGE_M3_MAX_TOKENS
🔐 secretPOWER_LLM_API_KEY
configPOWER_LLM_API_BASE
configPOWER_LLM_MODEL
configPOWER_QWEN3_RERANKER_MODEL
configPOWER_JINA_RERANKER_MODEL
configPOWER_BGE_RERANKER_ONNX_REPO
configPOWER_BGE_RERANKER_ONNX_REVISION
🔐 secretOPENROUTER_API_KEY
// quality suggestions

No access to sensitive paths

Reads sensitive paths: /etc/power/infra/credentials

Remove reads of sensitive system paths. If you genuinely need them, document why in the README.

Readable source code

1 file are minified or bundled, which is usually build output rather than concealment

Ship unminified, readable source.

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 2 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/weby-homelab/power-framework?variant=verified)](https://m8ven.ai/mcp/weby-homelab/power-framework)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 3cb94ff7f82d18c0f77b336848d1c34f220e58a3
code hash: 3b3aec500acf62f6f1e34681abf992ffae5f2be89b8582f71344ce31b8f6c44a
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