Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@agentsapi-sec-filings What are the latest 8-K filings?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AIGC: Label: "1" ContentProducer: 001191440300708461136T1XGW3 ProduceID: 920b5c8629efc4aabcea22970c4daaa6_b54ca5ffad0411f18039525400461939 ReservedCode1: KqzVXnEGI8Gcpo7Vcvy8qtyqbGOzj4N8S/k0gymQ95w8Re1g/gGRDviJoo284tPWUuqGz3JDVGV4678a9M6vBJeUmToR/X6mpVxfkk3rYnufIPZ+lyQiXbvc/zoHICST+dM6AtCI2MJI1GuuWSFPIPvixhu/+EP9XzA4GOxJJA//0QwVLRCXKzYf218= ContentPropagator: 001191440300708461136T1XGW3 PropagateID: 920b5c8629efc4aabcea22970c4daaa6_b54ca5ffad0411f18039525400461939 ReservedCode2: KqzVXnEGI8Gcpo7Vcvy8qtyqbGOzj4N8S/k0gymQ95w8Re1g/gGRDviJoo284tPWUuqGz3JDVGV4678a9M6vBJeUmToR/X6mpVxfkk3rYnufIPZ+lyQiXbvc/zoHICST+dM6AtCI2MJI1GuuWSFPIPvixhu/+EP9XzA4GOxJJA//0QwVLRCXKzYf218=
MCP server exposing SEC EDGAR filings as agent-callable tools — pay-per-call in USDC on Base via x402. No API key, no subscription: every call settles a micropayment on-chain and returns data immediately.
Tool | Description | Price |
| Latest 10-K / 10-Q / 8-K filings across US markets, newest first (max 40) | $0.01 USDC / call |
| Real-time 8-K material events stream (M&A, executive changes, earnings, delisting, bankruptcy) | $0.005 USDC / call |
| Free discovery: endpoints, prices, payment network, wallet | free |
Every paid response carries a receipt block (paid, payer, amount, transaction) so the caller can audit settlement.
Related MCP server: SEC EDGAR Filings MCP
Node.js >= 18
An EVM wallet holding USDC on Base (mainnet, eip155:8453) plus a small amount of ETH for gas on the first transfer
The private key is used locally to sign the x402 payment payload; it is never sent to the server
npx -y agentsapi-sec-filingsOr install globally:
npm install -g agentsapi-sec-filingsmirror (self-hosted tarball): https://agentsapi.top/downloads/agentsapi-sec-filings-1.0.0.tgz
Env var | Required | Default | Purpose |
| yes | — | EVM private key ( |
| no |
| Base RPC endpoint |
| no |
| API base URL |
{
"mcpServers": {
"sec-filings": {
"command": "npx",
"args": ["-y", "agentsapi-sec-filings"],
"env": {
"X402_PRIVATE_KEY": "0x<your-base-wallet-key>"
}
}
}
}{
"mcpServers": {
"sec-filings": {
"command": "npx",
"args": ["-y", "agentsapi-sec-filings"],
"env": { "X402_PRIVATE_KEY": "0x<your-base-wallet-key>" }
}
}
}"Any 8-K filings in the last few hours that look like M&A activity?"
The agent calls sec_filings_8k, the client answers the HTTP 402 challenge with a signed USDC transfer, and the filing list comes back with EDGAR links — $0.005 settled, no signup.
Tool call issues GET https://agentsapi.top/api/filings/8k
Server replies 402 Payment Required with x402 terms (USDC, Base, amount, payTo)
Client signs an EIP-3009 USDC authorization and retries with X-PAYMENT
Facilitator settles on-chain; server returns data + X-PAYMENT-RESPONSE receipt
Data is refreshed every 10 minutes; each response contains up to 40 filings.
No rate limits, no API keys — cost scales exactly with usage, which keeps agents free to call as needed.
MIT （内容由AI生成，仅供参考）
Real-time stream of SEC EDGAR 8-K current reports — material corporate events such as M&A, officer changes, earnings releases, delisting and bankruptcy. Sorted by filing time descending, max 40 per call. Paid per call: $0.005 USDC on Base, settled automatically over x402.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint=true, openWorldHint=true), the description adds concrete behavioral details: it is a real-time stream, sorted descending by filing time, capped at 40 per call, and has a per-call cost of $0.005 USDC settled via x402. This discloses rate limits, pricing, and stream semantics, exceeding what annotations alone provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loads the core purpose, and packs essential operational details (sorting, limit, pricing) without any fluff. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters, no output schema, and simple annotations, the description covers the main aspects: what data is returned, the ordering, the limit, and the cost. It does not specify the exact response structure, but that is not required given the absence of an output schema and the event-type examples already given.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so the description need not add parameter-level detail. According to the baseline rule for zero parameters, a score of 4 is appropriate; there is nothing to compensate for.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'stream' and the resource 'SEC EDGAR 8-K current reports', enumerates representative event types (M&A, officer changes, earnings releases, etc.), and distinguishes itself from siblings by focusing on real-time 8-K coverage specifically.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context: it is a real-time stream of 8-K events sorted by filing time, which implicitly tells when to use it (when real-time 8-K data is needed). However, it does not explicitly mention alternatives or exclusions relative to sibling tools like sec_filings_today, so it doesn't reach the 'explicit when/when-not' level.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free discovery endpoint: describes the available SEC EDGAR data endpoints, their prices, payment network and wallet address. Use this first to check pricing before calling a paid tool.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=trueable, and the description adds that it is free, that it lists endpoints/prices/payment details, and that it should be used before paid calls. This is useful context beyond the annotations, without contradicting them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no filler: the first states what the endpoint is and what it returns, the second tells the agent when to use it. Everything earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, read-only info endpoint, the description fully covers what the agent needs: the resource, the included content (pricing, payment network, wallet address), and its intended position in the workflow (use before paid calls). No output schema is needed for such a simple discovery endpoint, and the annotations already confirm safety.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and 100% schema coverage, so the baseline is already strong. The description adds that the call needs no arguments beyond indicating it is a discovery endpoint to check first, which is sufficient for a parameterless tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies a specific verb ('describes') and resource ('available SEC EDGAR data endpoints, their prices, payment network and wallet address'). It also labels the endpoint as a free discovery endpoint, which distinguishes it from the paid data endpoints it describes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs the agent to use it first to check pricing before calling a paid tool. This gives clear when-to-use guidance and implies it should not be used for actual data retrieval, which is handled by sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Latest SEC EDGAR filings across 10-K, 10-Q and 8-K form types, sorted by filing time descending (max 40 per call, refreshed every 10 minutes). Each item: form type, company name + CIK, filing time (UTC), EDGAR archive URL. Paid per call: $0.01 USDC on Base, settled automatically over x402.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the agent knows this is a safe read operation. The description adds valuable behavioral context beyond annotations: the 40-item cap, the 10-minute refresh cadence, the UTC timestamp format, and the per-call cost/settlement mechanism. It does not describe pagination or what happens when more than 40 filings exist, but the cap is explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with no wasted words. The core purpose is front-loaded, followed by the item shape and the cost/settlement detail. Every sentence earns its place, and the structure is easy to scan.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter read-only tool, the description is nearly complete: it covers scope, ordering, limits, refresh behavior, item fields, and cost. There is no output schema, so the description's item list partially compensates, but it doesn't specify the exact JSON shape or field names. The absence of pagination details is a minor gap given the explicit 40-item cap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema is trivially complete (100% coverage). The description adds meaning by explaining what the returned items contain (form type, company name + CIK, filing time, EDGAR URL) and the ordering, which is useful context even though there are no parameters to document. Baseline 4 for zero-param tools is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Latest SEC EDGAR filings'), a precise resource (10-K / 10-Q / 8-K form types), and a clear scope (sorted by filing time descending, max 40 per call). It distinguishes itself from siblings by naming the form types and the aggregation across them, so an agent can tell it apart from sec_filings_8k without opening any schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool: when you need a broad, recent cross-form-type view of SEC filings. It does not explicitly name the sibling alternative sec_filings_8k or state when to choose that instead, but the form-type scope and the 'max 40 per call' constraint give clear context. A brief exclusion ('for 8-K only, use sec_filings_8k') would make it a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.1sec_filings_8ksec_filings_service_infosec_filings_todayScored across 3 tools
The three tools are mostly distinct: sec_filings_today covers all form types, sec_filings_8k focuses specifically on 8-K filings, and sec_filings_service_info is a free metadata/pricing endpoint. There is slight overlap between sec_filings_today and sec_filings_8k since 8-Ks are included in the broader tool, but the descriptions clarify the different scopes.
All tool names follow a consistent sec_filings_ prefix with a descriptive suffix (today, 8k, service_info). The pattern is predictable, though 'service_info' is slightly less verb-oriented than the other two names.
Three tools is on the low end for a server, but the narrow purpose of SEC filings access makes the count reasonable. The inclusion of a free service info tool is useful, though the server could benefit from additional endpoints like a specific 10-K/10-Q filter or a company-specific lookup.
The server covers today's filings and a dedicated 8-K stream, which addresses the core use case of monitoring recent SEC EDGAR filings. However, it lacks obvious complementary operations such as searching by company/CIK, retrieving a specific filing's details, or filtering by date range, leaving notable gaps for a filings-focused API.
Pay-per-call tools for autonomous agents, settled in USDC on Base via x402.
Pay-per-call data APIs for AI agents. USDC on Base via x402. 33 tools, no signup.
Accountless public-source, SEC Form D and OFAC tools with x402 USDC payment on Base.
Market data and web intelligence for AI agents, paid per call in USDC on Base via x402.
