mcpbeat

Company Intelligence MCP Server

ai.velarion/company-intelligence
answering

Company Intelligence is answering right now. Last checked 15 min ago. It exposes 9 tools.

Exec comp benchmarking, say-on-pay risk, and governance cards for US public companies.

Uptime history 43 hours of history
43 hours agonow
100.0%
Uptime 24h
91 of 91 checks
9
Tools
read from the server
289 ms
Response time
average over 24h
open, no key
Access
streamable-http

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.

run in your terminal
claude mcp add company-intelligence --transport http https://velarion-scraper-production.up.railway.app/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "company-intelligence": {
      "url": "https://velarion-scraper-production.up.railway.app/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.company-intelligence]
url = "https://velarion-scraper-production.up.railway.app/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "company-intelligence": {
      "url": "https://velarion-scraper-production.up.railway.app/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "company-intelligence": {
      "url": "https://velarion-scraper-production.up.railway.app/mcp"
    }
  }
}

Available tools 9

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

benchmark
benchmark_executive_pay
Benchmark executive pay vs. disclosed peers using Velarion's canonical percentile data. Returns pay percentile, performance (TSR) percentile, P4P gap, and an alignment label based on canonical_metrics columns (ceo_percentile, tsr_percentile, p4p_gap). No LLM. role is currently CEO-only (only CEO percentile is pre-computed in canonical_metrics).
compare
compare_companies
Compare multiple companies on pay, performance, and governance metrics. Returns a ranked table from Velarion's canonical_metrics — no LLM narrative invention. The data-based summary describes observed patterns in the returned data only. Out-of-coverage tickers are excluded (listed separately). Max 20 tickers.
fulfill
fulfill_paid_order
Fulfill a paid custom quote by compiling and delivering its artifact. Ownership gate: you may only fulfill a quote your own agent account owns. (The REST buyer rail has always enforced this — routes.py:656 — and this tool did not, which meant any valid token could fulfill, and therefore download, an artifact somebody else had paid for. Latent while every token was owner-issued; a live artifact leak the moment self-serve issuance opened. Closed here.) Settlement gate (fail-closed): if the quote is priced and settlement is not verified on any rail, returns settlement_unverified — compile_and_deliver is NOT called. On verified settlement: calls compile_and_deliver (fulfillment.py:121) — the same path used by Danny and the agent bridge. No forked fulfillment logic.
generate
generate_governance_alpha_card
Generate a Governance Alpha Card for a company. Composite deterministic card: pay alignment (Velarion's own P4P-style estimate, modeled on public proxy-advisory methodology concepts — not licensed ISS data), governance scorecard, SoP risk band, peer quality, top risks/strengths. Requires the company to be in Velarion's coverage universe with current-period data. Calls generate_alpha_card (lib/agent_merchant/compilers/governance_alpha_card.py:441) after confirming deliverability via evaluate_deliverability (deliverability.py:219), which includes the period-currency gate (_governance_alpha_card_period_gate at :312). FREE-TIER CAP: this is the free sample of a $100 marketplace product (GOVERNANCE-ALPHA-CARD, pricer.py:59). Each agent gets ALPHA_CARD_FREE_DAILY_CAP cards per UTC day; beyond that the tool returns free_tier_cap_reached with the purchase path. Unlimited free issuance of the paid anchor product is the contradiction the catalog's PRICE_INTEGRITY blocker named — the cap is what resolves it. Structured errors returned (not raised) for: - not_in_coverage: ticker unknown - not_deliverable: coverage too thin / stale period - free_tier_cap_reached: daily free allowance spent (buy it, or wait for 00:00 UTC)
lookup
lookup_company_compensation
Look up executive compensation for a company in Velarion's coverage universe. Returns CEO/NEO total compensation, pay mix breakdown, and canonical metrics for the requested fiscal year (latest available if omitted). All data sourced from Supabase production tables — no LLM, no invented values. Out-of-coverage tickers return a structured error (not_in_coverage).
place
place_order
Place an order for a priced product — creates a quote you can pay and then fulfill. This is the missing middle of the buy path: price_product tells you what it costs, place_order creates the actual quote (owned by YOUR agent account), and fulfill_paid_order delivers it once settlement clears. Requires a token with the mcp:buy scope AND a Velarion commerce account — a self-serve token issued at POST /agent/v1/token/self-serve has both. CUSTOM-* cohort products (CUSTOM-PEER-COHORT / CUSTOM-SOP-WINDOW / CUSTOM-GOV-EXTENDED): the ticker list is the comparison cohort, capped at 15 distinct tickers (a 16th is a clean too_many_tickers rejection, never a silent truncation). The subject is the first in-coverage ticker unless subject_ticker names another cohort member. Returns quote_id, the price, and how to pay. Nothing is charged here.
predict
predict_say_on_pay_risk
Predict Say-on-Pay risk for a company using Velarion's deterministic risk compilers. Returns trend phrase, peer cohort distribution note, governance friction summary, and overall risk band. No LLM — fully deterministic from canonical_metrics + say_on_pay data. Compilers: compile_sop_trend_phrase, compile_sop_peer_cohort_distribution, compile_governance_friction_summary (lib/agent_merchant/compilers/say_on_pay_risk.py).
price
price_product
Price a Velarion product. Handles EVERY catalog SKU in its real state. product_type may be a sku_id (e.g. "SKU-002") OR a custom_artifact_family (e.g. "peer_disclosure_custom_cohort"). Returns the row's classification and, when APPROVED_SELLABLE, the price a buyer is actually charged: - APPROVED_SELLABLE → proposed_price_cents + currency + fulfillment_type + latency + caveats. No price floor touches it (deleted 2026-07-14); the catalog/pricer anchor IS the billed price. - NEEDS_OWNER_APPROVAL → {status: "needs_owner_approval"} structurally — price is known but the row is pending Andy's approval flip. - UNSELLABLE / KILLED → structured error with the reason. custom_band families price via the profit-aware pricer (respecting MERCHANT_MIN_MARGIN); one_off_fixed SKUs price at the canonical catalog price_cents. No fabricated price is ever returned (price_verified gate enforced upstream in classify_sku).
skus
list_skus
List the Velarion catalog — every product an agent can see and (where APPROVED_SELLABLE) buy. Returns all APPROVED_SELLABLE SKUs with full detail by default (sku_id, name, price, currency, fulfillment type, latency, caveats, classification). Set include_non_sellable=true to also return NEEDS_OWNER_APPROVAL / UNSELLABLE / KILLED rows, each clearly tagged with its classification and blockers so inventory is never hidden — only de-prioritized. No price is fabricated: unverified prices are surfaced as-is with their classification, never quoted as billable.

Endpoints

URLTransportStateLatencyChecked
https://velarion-scraper-production.up.railway.app/mcp streamable-http answering 270 ms 15 min ago

Company Intelligence — questions

Answers built from our own checks of this server.

What can Company Intelligence do?
It exposes 9 tools, read directly from the server on our last check. Among them: benchmark_executive_pay, compare_companies, fulfill_paid_order, generate_governance_alpha_card, list_skus, lookup_company_compensation and 3 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Company Intelligence working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 289 ms. The bar chart above shows every period we have measured.
How do I connect Company Intelligence?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Company Intelligence need an API key?
No. Company Intelligence completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 9 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Company Intelligence?
It answers our handshake in 289 ms on average, which is faster than 48% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.