
Veris
Gives your agent web search, clean page reads, and SEC EDGAR filings with full provenance metadata attached to every fact. You get `web_search` (Brave or DuckDuckGo), `web_read` for markdown plus publish date, author, content hash, and license, and a set of finance tools that pull official SEC filings by ticker or CIK. The EDGAR integration is particularly clean because filing dates and accession numbers come straight from the SEC, so provenance is authoritative rather than scraped. Also ships with `watch_check` for monitoring URLs or company filings for changes. Runs via stdio or as a remote HTTP server with optional API key auth. Reach for this when you need citations and source tracking baked into every web operation.
- tools
- 8
- auth
- Secret needed
- transport
- STDIO
- env vars
- 2
- last updated
- Oct 10, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
web_searchRanked results as structured JSON. Brave (with key) or keyless DuckDuckGo.
Ranked results as structured JSON. Brave (with key) or keyless DuckDuckGo.
No parameter schema in public metadata yet.
web_readURL → clean markdown + provenance block. 24h cache.
URL → clean markdown + provenance block. 24h cache.
No parameter schema in public metadata yet.
web_researchSearch + read top N + bundle with per-source citations.
Search + read top N + bundle with per-source citations.
No parameter schema in public metadata yet.
finance_filingsTicker / name / CIK → recent SEC filings: form, official filing & report dates, accession, direct document URL.
Ticker / name / CIK → recent SEC filings: form, official filing & report dates, accession, direct document URL.
No parameter schema in public metadata yet.
finance_filing_readRead a filing by URL, or auto-read the latest matching form for a company. Clean text + provenance.
Read a filing by URL, or auto-read the latest matching form for a company. Clean text + provenance.
No parameter schema in public metadata yet.
finance_financialsRevenue, net income, total assets, cash, diluted EPS from SEC XBRL — each figure stamped with the exact filing it came from.
Revenue, net income, total assets, cash, diluted EPS from SEC XBRL — each figure stamped with the exact filing it came from.
No parameter schema in public metadata yet.
watch_manageAdd/remove/list watches: a company's SEC filings (ticker + optional form like 8-K) or any URL (content-hash watch).
Add/remove/list watches: a company's SEC filings (ticker + optional form like 8-K) or any URL (content-hash watch).
No parameter schema in public metadata yet.
watch_checkCheck all watches; returns only what's NEW (new filings / changed pages) and rolls baselines forward.
Check all watches; returns only what's NEW (new filings / changed pages) and rolls baselines forward.
No parameter schema in public metadata yet.
Sponsors
Configuration
BRAVE_API_KEYsecretOptional Brave Search API key; falls back to keyless DuckDuckGo if unset.
SEC_USER_AGENTSEC fair-access User-Agent ('Name email@domain') for EDGAR; a default ships.
Readme
veris
Provenance-first web access for AI agents. Clean content plus verifiable source metadata, in one call.
Today an AI agent reading the web gets a wall of text. It does not get: when the page was published, whether the content changed since last time, who wrote it, the canonical source, or the license terms. veris attaches all of that to every read.
web_read("https://example.com/article")
→ clean markdown
+ { publishedAt, modifiedAt, author, canonicalUrl, contentHash, license, fetchedAt }
That metadata is not a nice-to-have. It is the foundation the rest of the AI-web economy needs: freshness, change-detection, citation, and — eventually — paying the people who wrote the content.
Why this exists
Details
- Repository
- github.com/jakeyoung1/veris
- Category
- Data & Analytics
- Package
veris-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active