Gives AI agents verified end-of-life and end-of-support dates, risk scores and exploited-vulnerability exposure for 600+ software, OS and hardware products.
The endoflife.ai MCP server lets an AI agent answer lifecycle questions from verified data instead of from memory: is this version still supported, when does support end, what should it be upgraded to, and is an end-of-life version exposed to a vulnerability that attackers are using today.
It covers 600+ products across operating systems, databases, language runtimes, frameworks, browsers, network and edge devices and cloud services. Every answer carries the source of the date, so an agent can cite where it came from. Components can be looked up by name and version, by package URL, or in bulk from a CycloneDX or SPDX SBOM; a component we cannot match is reported as unmatched with a reason and is never guessed.
The server is remote (streamable HTTP), read-only, and needs no account, no API key and no installation. An optional endoflife.ai API key raises rate limits.
Highlights
Ten read-only tools: check a version, score risk, scan a whole stack, audit an SBOM, list what reaches end of life next, find the upgrade path, and check exploited-vulnerability exposure.
Every date is labelled with its source, the vendor's own lifecycle page for the products we verify directly; unmatched components are reported, never guessed.
No sign-up, no key, nothing to deploy: point any MCP client at one HTTPS endpoint.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
This listing has one pricing dimension: a single Free usage option with no charge. There are no tiers, instance sizes, or usage add-ons to compare. You access the hosted server at no cost. The Free dimension covers your use of the end-of-life and support date lookups through this listing. Because only one option exists, pricing does not scale or vary by quantity, term, or volume. Billing stays at zero for this dimension.
Top-of-mind questions for buyers
What does the Free dimension on this listing actually give me access to?
You get access to the hosted server for software end-of-life and support date lookups. It covers lifecycle data across hundreds of tracked products. The listing meters nothing, so there is no per-request, per-user, or per-product charge tied to this dimension.
Does my cost change if I run many lookups or query many products?
No. The Free dimension carries a zero charge regardless of how many lookups you run or products you check through this listing. Cost does not scale with request volume, query frequency, or the number of products you track. Billing stays at zero.
Is there any usage threshold on this listing that would trigger a charge?
No threshold on this listing triggers a charge. The single Free dimension has no committed amount, no overage point, and no tier boundary. Nothing in your usage moves you to a paid state. For needs beyond this listing's scope, contact the vendor.
endoflife.ai
Helpful?
Vendor refund policy
Not applicable. The product is free of charge; no payment is collected, so there is nothing to refund. Questions: partners@endoflife.ai.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
MCP
API
endoflife.ai MCP Server: end-of-life and end-of-support dates, EOL Risk Scores and CISA KEV exposure for 500+ software products, as a remote MCP server for AI agents.
PREREQUISITES: any MCP client that supports remote servers over Streamable HTTP (Claude Desktop, Cursor, VS Code, Amazon Q Developer, others); outbound HTTPS to https://mcp.endoflife.ai. No account or key is required.
AUTHENTICATION AND RATE LIMITS
Keyless: no credentials; 50 tool calls per day per client, burst limit 60 requests per minute per address.
With a key: header X-API-Key: <key>. Quotas: free evaluation key 150 requests per day for 30 days; Starter 10,000 per day; Pro and above as listed at https://endoflife.ai/api. Keys are issued, rotated and revoked at https://endoflife.ai/api.
TOOLS AND PARAMETERS (* = required; product and version are endoflife.ai slugs and cycles, e.g. postgresql / 14, windows-server / 2019; use list_products to find a slug)
get_upgrade_path(product*: string, version: string) - supported target versions with dates and scores.
check_sbom(sbom*: object (CycloneDX or SPDX JSON), max_items: integer) - map SBOM components to products.
EXAMPLE REQUEST (curl, keyless)
curl -s -X POST https://mcp.endoflife.ai -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"check_eol","arguments":{"product":"postgresql","version":"14"}}}'
EXAMPLE RESPONSE (abbreviated)
{"jsonrpc":"2.0","id":1,"result":{"content":[{"type":"text","text":"{...}"}],"structuredContent":{"product":"postgresql","version":"14","status":"warn","is_eol":false,"is_supported":false,"eol_approaching":true,"eol_date":"2026-11-12","days_until_eol":35,"days_past_eol":null,"latest_release":"14.24","cpe":["cpe:2.3:a:postgresql:postgresql"],"eol_date_source":"vendor-fetched","eol_date_verified_at":"2026-10-03","eol_date_confidence":"high","score_url":"https://endoflife.ai/score/postgresql/14"}}}
Full response schema per tool: see the API usage instructions below.
ERROR CODES
Tool errors come back as an MCP result with isError true and a text message (HTTP 200, per the MCP spec): unknown product or version -> "Error: No data for <product> <version>. Use list_products to find the canonical slug."; missing required parameter -> "Error: Both "product" and "version" are required." (per tool); unknown tool -> "Error: Unknown tool: <name>". Transport errors: HTTP 429 when a daily or per-minute limit is exceeded (wait for the reset or add a key); an unrecognised or expired X-API-Key is not rejected, the call is served keyless; malformed JSON-RPC -> JSON-RPC error object; HTTP 5xx -> retry with backoff.
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Asana offers a Model Context Protocol (MCP) server, accessible via app integration, which allows AI assistants and other applications to access the Asana Work Graph from beyond the Asana platform. This server provides a way to interact with your Asana workspace through various AI platforms and tools that support MCP.
Tavily MCP is a lightweight server that enables AI assistants to perform real time web search, intelligent crawling, and structured data extraction through the Model Context Protocol (MCP).
Connect your favorite AI tools like GitHub Copilot, Claude, and Cursor directly to BrowserStack end-to-end testing stack, all from within your IDE. BrowserStack MCP Server is a secure, open-source bridge that enables natural language test management, execution, debugging, and accessibility scans seamlessly.
The Wiz Model Context Protocol (MCP) Server acts as an MCP-compatible service that translates plain-language queries into Wiz-specific operations, like querying resources, or assessing risks.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.