company-brain-mcp (vanshsohi-zenduit/company-brain-mcp) is an MCP server listed on the M8ven Trust Index. It scores 52 out of 100, grade D. It declares 16 tools. No publisher has claimed this listing.
Enables AI agents to query and manage company knowledge from a Supabase GraphRAG store, including accounts, meetings, people, org hierarchy, product docs, and call logs.
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
vanshsohi-zenduit
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.
get_account_context_graphFetch the full account context graph for an account: Org → MENTIONS → Meetings → PARTICIPATED_IN → Persons + TAGGED_WITH → Tags. Returns a rich JSONB skeleton used by the CS chat pipeline. Requires sql/018 to be applied.
get_account_health_signalsGet health signals across all customer accounts: churn/risk signal counts, days since last meeting, NPS, account health status, and expansion signals. Use risk_only=true to surface only at-risk accounts.
get_account_summaryGet a summary of a customer account: top signal tags, recent meetings, and context chunks. Returns account health metadata from Zoho CRM plus brain-extracted signal data.
find_similar_accounts_by_descriptionFind existing customer accounts most similar to a prospect description. Returns customer accounts ranked by industry match first, then semantic similarity. Use this for social proof when pitching to a prospect: "here are customers like you that we already serve." Takes a free-text description — the …
find_accounts_by_tagFind all accounts where specific tag signals appear (e.g. churn_risk, feature_request, pricing_concern). Returns accounts ranked by aggregate tag weight — the higher the weight, the more strongly the signal appeared across their meetings. Use query_tag_trends to discover available tag slugs first.
find_similar_accountsFind accounts with similar signal profiles to a reference account, using shared tag weight overlap. Useful for benchmarking (how do at-risk accounts compare?) or finding clusters of accounts with the same pain points.
get_account_factsGet aggregate facts about an account: total meeting count, date range, top tags by weight, and meeting type distribution. Returns empty if the account is not in the brain.
get_meeting_transcriptRetrieve the full transcript of a specific meeting assembled from chunks in reading order. Call list_account_meetings first to obtain the meeting_id. Returns all transcript chunks with speaker names where resolved.
get_org_hierarchyGet the GoFleet/ZenduIT internal org chart: Tribes (top-level departments), Pods (sub-divisions), and Chapters (cross-pod discipline groups), each with their current leader. Use to find who to escalate to or which team owns a function.
get_person_meetingsGet all meetings a specific person has participated in across all accounts, in reverse chronological order. Use to understand a contact's history, prepare for handoffs, or map relationships between people and accounts.
list_account_meetingsList meetings for a specific account or globally across all accounts. Supports ordering, type filtering, and date range filtering. Returns meeting metadata including type, date, duration, and tag slugs.
query_tag_trendsAggregate signal tag trends across meetings. Shows which tags (product_gap, churn_signal, competitive_intel, etc.) appear most, across how many accounts and meetings, with sample account names. Works globally or scoped to one account.
search_call_logSearch RingCentral phone-call events by phone number, participant, and/or direction. Returns per-call detail (direction, from/to number + name, duration) plus a direction breakdown counting ALL matching calls. Use for questions like "was this call inbound or outbound?", "do we have any calls on <num…
search_meeting_chunksSemantic search across meeting transcript chunks using 3-leg hybrid retrieval (HNSW vector + full-text + tag signal). Scope to an account or search globally. Optionally filter by tag slugs or recency. Returns ranked transcript excerpts with meeting context.
search_peopleSearch for people (employees or external contacts) by name or email. Returns their org affiliation, internal/external status, and meeting count in the brain. Useful for finding account contacts, relationship mapping, or looking up who attended a meeting.
search_product_docsSemantic search across the company product knowledge base: feature specs, competitor battlecards (vs Samsara, Motive, Lytx, etc.), objection-handling scripts, ICP profiles, and value propositions. Use this when a question is about our products, their capabilities, how they compare to competitors, or…
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
ALLOWED_ORIGINSGEMINI_API_KEYMCP_API_KEYMCP_PORTPORTSUPABASE_SERVICE_ROLE_KEYSUPABASE_URLTool 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 — get_account_context_graph (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_account_health_signals (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_account_summary (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
10/16 tool handlers declare input schemas (63%)
Declare an inputSchema with zod/joi/yup on every tool definition.
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.
Secrets stay with their owner
1 secret sent to a request target we could not resolve (GEMINI_API_KEY → dynamic) — often a configured endpoint, not necessarily third-party
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
Secrets not logged
1 secret value sent to error
Redact or omit secret values from log output.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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/vanshsohi-zenduit/company-brain-mcp)?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