Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the AgentFilings, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fagentfilings.com%2Fagentfilings" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fagentfilings.com%2Fagentfilings" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with AgentFilings API.
Retrieve the latest SEC filings for a ticker, optionally filtered by form type
Read a structured earnings summary built from XBRL company facts without parsing PDFs
List Form 4 insider transactions for a ticker since a given date
Probe coverage, freshness timestamps, and per-endpoint pricing before paying
Patterns agents use AgentFilings API for, with concrete tasks.
GET STARTED
★ Agent Filing Lookup via Jentic
An AI agent researching a company can pull structured filings instead of scraping EDGAR. Through Jentic the agent calls the free probe to confirm coverage and pricing, then retrieves the latest filings for a ticker as clean JSON, filtering by form type when it only wants a specific disclosure.
Call the probe endpoint to confirm coverage, then retrieve the latest filings for a given ticker filtered to a specific form type
Earnings Analysis from XBRL
Analysts need earnings figures without hand-parsing financial statements. AgentFilings returns an earnings summary derived directly from XBRL company facts, so an agent reads normalized numbers as JSON rather than extracting them from a PDF, and the data is public-domain SEC information kept pre-parsed and current.
Read the structured earnings summary for a ticker and extract the latest reported revenue and net income figures
Insider Transaction Monitoring
Investors watch insider buying and selling for signal. AgentFilings lists Form 4 insider transactions for a ticker since a chosen date as clean JSON, so an agent polls for new filings on a watchlist and flags notable buys or sales without reading raw filings.
List Form 4 insider transactions for a ticker since last week and flag any purchases above a chosen size
5 endpoints — the agentfilings api serves structured us sec and edgar filing data to autonomous agents as clean json.
METHOD
PATH
DESCRIPTION
/filings/latest
Latest filings for a ticker, optionally filtered by form type
/earnings/summary
Structured earnings summary from XBRL company facts
/insiders
Form 4 insider transactions for a ticker since a date
/probe
Coverage, freshness timestamps, and per-endpoint pricing
/filings/latest
Latest filings for a ticker, optionally filtered by form type
/earnings/summary
Structured earnings summary from XBRL company facts
/insiders
Form 4 insider transactions for a ticker since a date
/probe
Coverage, freshness timestamps, and per-endpoint pricing
What agents get from Jentic-routed access to this vendor.
Setup
Wiring AgentFilings by hand means calling the probe endpoint first to read coverage and per-endpoint pricing, then settling paid calls with x402 USDC on Base while leaving the free health and probe endpoints open. Through Jentic you install once, import AgentFilings from the API Directory, and your agent reads filings, earnings, and insider data.
Permission scoping
AgentFilings carries no resource id in its paths, so rules bound which operations your agent may call rather than which ticker. You can allow only the filings and earnings reads, so the agent retrieves company data and nothing else, and the insider-transactions endpoint stays out unless you add it.
Credential isolation
AgentFilings needs no API key: its free endpoints are open and paid endpoints settle with x402 on Base, so there is no secret for Jentic to hold. When you add APIs that do use keys, your own Jentic One instance keeps them encrypted and injects them at execution time, never in the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get the latest filings for a ticker' or 'read a company's earnings summary', and Jentic returns the matching AgentFilings operation with its input schema so the agent calls the right endpoint directly.
Alternatives and complements available in the Jentic catalogue.
Specific to using AgentFilings API through Jentic.
What authentication does the AgentFilings API use?
The AgentFilings API requires no credential per its OpenAPI spec: the health and probe endpoints are free and open, and the filings, earnings, and insider endpoints are paid, settling with x402 using USDC on Base. There is no key to manage, so an agent calls the free probe first to read coverage and pricing before paying. Through Jentic the operations are imported from the API Directory and called directly.
Is there an AgentFilings MCP server?
You don't need an MCP server to give your agent AgentFilings. Jentic connects it directly from the API Directory: import AgentFilings and your agent reads filings, earnings, and insider data straight away. Operations are discovered on demand, so no extra server's tool definitions sit in your agent's context.
Can I limit what my agent is allowed to do with the AgentFilings API?
Yes. AgentFilings carries no resource id in its paths, so rules bound which operations the agent may call rather than which ticker. You can allow only the filings and earnings reads, so the agent retrieves company data and nothing else, and the paid insider-transactions endpoint stays out of the rule unless you add it.
Can I get a company's earnings with the AgentFilings API?
Yes. The earnings summary endpoint returns a structured summary built from XBRL company facts, so you read normalized figures as JSON without parsing a PDF. The data is public-domain SEC information kept pre-parsed, and the probe endpoint reports how fresh it is before you request it.
What are the rate limits for the AgentFilings API?
The AgentFilings OpenAPI spec does not publish request rate limits. Pricing is per endpoint and is returned by the free probe endpoint along with coverage and freshness timestamps, so an agent checks cost and availability before paying with x402. Check the AgentFilings documentation at https://agentfilings.com for current details.
How do I get SEC filings with the AgentFilings API through Jentic?
Search the Jentic API Directory for an intent like 'get the latest filings for a ticker', import AgentFilings, and your agent calls the probe and filings operations through Jentic. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Fetch structured US SEC filings, XBRL-derived earnings summaries, and Form 4 insider transactions for a ticker as clean JSON. Free health and probe endpoints; paid endpoints settle with x402.
Use for: I need the latest filings for a ticker, Get a structured earnings summary for a company, List recent insider transactions for a ticker, Check coverage and pricing before paying for a call
Not supported: Does not handle real-time stock quotes, order execution, or non-US filings. Use for structured US SEC filing, earnings, and insider data only.
The AgentFilings API serves structured US SEC and EDGAR filing data to autonomous agents as clean JSON. It returns the latest filings for a ticker with an optional form-type filter, a structured earnings summary derived from XBRL company facts without any PDF parsing, and Form 4 insider transactions for a ticker since a given date. The underlying data is public-domain SEC information, pre-parsed and normalized, and a free probe endpoint reports coverage, freshness timestamps, and per-endpoint pricing so an agent can decide before paying. Paid endpoints settle with x402 using USDC on Base, while the health and probe endpoints are free.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>