This server enables agents to discover, preview, and purchase structured SEC EDGAR filing data with AI-ready metadata and financial signals via three tools:
search_filings: Discover filings from a catalog of 10,000+ SEC filings by filtering on ticker, form type (10-K, 10-Q, 8-K, etc.), company name, fiscal period, or CIK. Returns agent readiness scores, EDGAR URLs, and optional one-liner summaries. Supports pagination.
get_filing_sample: Retrieve a free compact preview of a specific filing (by document_id), including an agent summary and financial metrics — useful for evaluating data quality before purchasing.
purchase_filing: Acquire the full filing JSON via a two-step on-chain USDC payment (x402 flow on Polygon or Base). Full data includes alpha signals, evidence-verified causality events, and detailed financial metrics not available in the free sample.
The three tools are designed for a structured agent workflow — search → sample (free) → purchase (paid) — minimizing cost while allowing quality evaluation before committing to a purchase.
Provides access to SEC EDGAR structured filings stored in a Supabase database, enabling search, preview, and purchase of filing data.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
# sec-filings-mcp
SEC EDGAR structured filing MCP for agents: search_filings, get_filing_sample, purchase_filing. Data lives in Supabase views (fi_listings_portfolio, fi_listings_portfolio_compact) populated by the finance-factory pipeline.
Read first | File |
Try without xpay key | docs/TRY_WITHOUT_XPAY.md — Glama sandbox or Cloud Run upstream |
Distribution (you vs repo) | |
Build / handoff | |
Env template | .env.example → copy to |
Glama | glama.json ( |
A2A / x402 | docs/A2A.md — Agent Card + payment mapping |
MCP Registry |
|
Discovery URLs |
Template reference: mcp_server.py (patent MCP, unmodified). Runtime: mcp_server_finance.py.
Layer | How to use |
MCP (production) | xpay URL below — |
A2A (discovery) | Agent Card on Cloud Run upstream (xpay blocks |
x402 (payment) |
|
Native A2A JSON-RPC task API is on the roadmap; today agents invoke via MCP Streamable HTTP. Details: docs/A2A.md.
Related MCP server: sec-edgar-mcp
Path | URL / action |
Glama sandbox | Open server → Try in Browser |
Cloud Run trial |
|
Details: docs/TRY_WITHOUT_XPAY.md.
xpay proxy always needs a key; per-tool $0 is allowed on xpay (docs) but is not the same as “no signup.”
Endpoint | URL |
xpay (billing + catalog) |
|
Cloud Run (upstream) |
|
Register / manage on xpay.tools. Slug: sec-edgar-filings.
Publisher checklist (finance collection, awesome list): docs/DISTRIBUTION.md.
git clone https://github.com/stagproject/sec-filings-mcp.git
cd sec-filings-mcp
copy .env.example .env
# Edit .env with Supabase + x402 keys
uv sync
# Run once in Supabase SQL Editor: sql/fi_processed_transactions.sql
uv run python mcp_server_finance.py --sse
# MCP: http://127.0.0.1:8081/mcp (PORT in .env)Tests:
uv run python test_finance_mcp.py
uv run python test_finance_mcp.py --xpay-only --e2egcloud run deploy sec-filings-mcp `
--source . `
--region us-central1 `
--allow-unauthenticated `
--port 8080Set env vars from .env (not committed). Do not deploy .env.cloudrun.yaml to git.
Listed at glama.ai/mcp/servers/stagproject/sec-filings-mcp — use Try in Browser for a no-key sandbox; production traffic uses xpay or Cloud Run above.
io.github.stagproject/sec-filings-mcpPublish / update: docs/MCP_REGISTRY.md. Search: https://registry.modelcontextprotocol.io
MIT — see LICENSE.md.
Free preview of one SEC filing (agent-friendly compact row from fi_listings_portfolio_compact). [COST: $0] Includes agent_summary and financial_metrics (CompanyFacts-derived) but NOT full alpha_signals / causality_events — those ship only via purchase_filing after x402 payment. Compare with purchase_filing: sample = evaluate quality; purchase = full evidence-backed JSON.
[EXAMPLE ARGUMENTS - MAXIMAL]: {"document_id": "000000708426000023"}
Inputs: document_id. Returns: result
Purchase and deliver one full SEC filing row from fi_listings_portfolio (MPP v1.0 x402). [COST: xpay per-call + on-chain USDC data price (see FINANCE_FILING_PRICE_USD)] Full JSON includes alpha_signals with evidence_verified causality_events and financial_metrics from SEC CompanyFacts. Do NOT return agent_bundle or internal pipeline fields.
[AGENTIC WORKFLOW — mandatory 2-step 402 flow]: STEP 1: Call with document_id and network only; leave tx_hash EMPTY. STEP 2: Broadcast the exact transaction_payload on-chain (polygon USDC default). STEP 3: Call again with the same document_id, network, and confirmed tx_hash (66 chars).
[EXAMPLE ARGUMENTS - MINIMAL (Step 1 — payment info)]: {"document_id": "000000708426000023", "network": "polygon"}
"document_id": "000000708426000023", "network": "polygon", "tx_hash": "0x1234567890abcdef1234567890abcdef1234567890abcdef1234567890abcdef" }
Inputs: document_id (required), network, tx_hash. Returns: result
PRIMARY discovery tool — lightweight catalog over 10k+ SEC filings (fi_listings_portfolio). [COST: low xpay per-call fee] Does NOT return alpha_signals, causality_events, or financial_metrics (use get_filing_sample / purchase_filing). Always returns agent_readiness_score (higher = better structured data) and edgar_url.
Required: at least one of ticker, form_type, company_name, fiscal_period, cik (avoids full-table scans).
Agent workflow after this call:
Shortlist by agent_readiness_score and optional agent_one_liner
get_filing_sample(document_id) — free preview
purchase_filing(document_id) — paid full JSON (x402)
[EXAMPLE ARGUMENTS - MINIMAL]: {"ticker": "AAPL", "limit": 5}
"ticker": "ADM", "form_type": "10-Q", "company_name": "Archer", "fiscal_period": "2026Q1", "min_agent_readiness_score": 70, "limit": 20, "offset": 0, "include_one_liner": true }
[EXAMPLE ARGUMENTS - PAGINATION (page 2)]: {"ticker": "MSFT", "form_type": "10-K", "limit": 10, "offset": 10}
Inputs: ticker, form_type, company_name, fiscal_period, +5 more. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a distinct purpose: search_filings for discovery, get_filing_sample for free preview, purchase_filing for full purchase. No overlap in functionality.
All tools follow a consistent verb_noun pattern: search_filings, get_filing_sample, purchase_filing. Naming is clear and predictable.
With only 3 tools, the set is minimal but appropriately scoped for a discovery-preview-purchase workflow. Slightly thin but reasonable for this paid data service.
The workflow covers search, free preview, and paid full access. No obvious gaps for the stated purpose, though additional metadata tools could be added.
Company enrichment + SEC EDGAR filings, financials, insider trades for agents; $0.01 USDC via x402
SEC EDGAR company lookup, filings, XBRL financials and filing text. Pay per call in USDC via x402.
SEC/XBRL issuer intelligence for crypto public companies via MCP, OpenAPI, x402, and MPP.
SEC EDGAR financials, benchmarks, screening & Buffett value scans for agents. Pay x402 or API key.