Skip to main content
Glama
sap-pam

sap-pam

by sapien47

SAP Support Radar: PAM web app + MCP server

"Which of our SAP systems are running out of support?": answered in seconds, for people and for AI assistants, from the official SAP Product Availability Matrix (PAM).

SAP offers no public API for PAM. It does let any S-user export it as a CSV file. This project turns that export into:

  1. A web app (deployable to SAP BTP) with a dashboard, a searchable product list and a My landscape risk check.

  2. An MCP server, so an AI assistant (Claude, Joule, Copilot or any MCP client) can answer support questions with the complete data instead of guessing from the web.

No SAP data is included or uploaded anywhere. Everyone brings their own PAM export. The web app reads it inside the browser; the MCP server reads it from a local file.

                      ┌─► Web app (SAP BTP, static)  → for people: dashboard, filters, landscape check
PAM CSV export ───────┤
                      └─► MCP server (local)         → for AI: ask questions in plain language

What it adds on top of a PAM viewer

Feature

What you get

Upgrade path

For every system: the newest released version of the same product with longer support, any announced version, and SAP's strategic successor where one exists (e.g. ERP → S/4HANA, Solution Manager → Cloud ALM).

What changed

Compare two PAM exports and see what SAP moved: dates extended or shortened, products newly in customer-specific maintenance, new or removed versions. Changes that affect your landscape are flagged.

Forgiving landscape matching

Paste system names as people actually write them ("ECC6 ehp2", "Solman", "BOBJ 4.3"), with "did you mean" when unsure.

AI access (MCP)

The same answers inside Claude or another AI assistant, e.g. "read this design document and tell me what runs out of support and what to upgrade to".

Upgrade path example

System

Recommended next version

Announced

Strategic successor

NW 7.4

SAP NETWEAVER 7.5 (mainstream to 31.12.2027, extended to 31.12.2030)

–

–

BOBJ 4.3

SBOP BI PLATFORM 2025 (to 31.12.2027)

SBOP BI PLATFORM 2029 (to 31.12.2031)

–

ECC6 ehp2

EHP8 FOR SAP ERP 6.0 (to 31.12.2027, extended to 31.12.2030)

–

SAP S/4HANA 2025 (to 31.12.2032)

ASE 16.0.4

SAP ASE 16.1 (to 31.12.2032)

–

–

Solman 7.2

latest version listed

–

SAP Cloud ALM (not in PAM)

Same-product recommendations come straight from PAM data. "Strategic successor" is a short, hand-maintained list of SAP's general direction (app/insights.js), not a PAM link.

What changed example

PAM gives no change log. Upload this month's export and the app compares it with the previous one, which it keeps automatically:

Product

Change

Before → after

⚠ SAP ASE 16.0.4

supported shorter

End of mainstream maintenance 31.12.2028 → 31.12.2027

⚠ EHP2 FOR SAP ERP 6.0

status worse

Unrestricted available → In customer-specific maintenance

SAP NETWEAVER 7.5

date published

End of extended maintenance – → 31.12.2030

SBOP BI PLATFORM 2025

supported longer

31.12.2026 → 31.12.2027

SAP S/4HANA 2025

new

Newly listed

Illustration made with a simulated older export; it is not a real SAP change log.

Related MCP server: Claude Data Buddy

Write system names the way people do

Landscape lists are rarely written in PAM's official wording. A shared matcher (app/matcher.js, used by both the web app and the MCP server) understands shorthand and typos:

You write

Matched PAM product version

ECC6 ehp2

EHP2 FOR SAP ERP 6.0

NW 750 · Netwaever 7.5

SAP NETWEAVER 7.5

Solman 7.2

SAP SOLUTION MANAGER 7.2

BOBJ 4.3 · Business Objects 4.3

SBOP BI PLATFORM 4.3

S4 2023 · bw4hana 2021

SAP S/4HANA 2023 · SAP BW/4HANA 2021

HANA DB 2 · R3 4.6C

SAP HANA PLATFORM EDITION 2.0 · SAP R/3 4.6C

It never guesses silently:

  • A version number you type must appear in the product version (7.4 is never matched to 7.5).

  • When candidates tie (e.g. netweaver without a version) or the match is weak, it asks "did you mean…" instead.

  • Every automatic match shows what was originally typed, so a person can confirm it.

npm test checks 25 real-world spellings against the PAM data, plus upgrade-path and export-comparison logic on a built-in fixture.

Example: checking a (fictional) landscape

Risk

Typed as

PAM product

Why

high

NW 7.40

SAP NETWEAVER 7.4

Mainstream maintenance ended 31.12.2020; customer-specific maintenance only

high

ECC6 ehp2

EHP2 FOR SAP ERP 6.0

Mainstream maintenance ended 31.12.2025

medium

BOBJ 4.3

SBOP BI PLATFORM 4.3

Mainstream maintenance ends 31.12.2026

low

ECC6 ehp8

EHP8 FOR SAP ERP 6.0

Mainstream until 31.12.2027, extended until 31.12.2030

low

S4 2023

SAP S/4HANA 2023

Mainstream until 31.12.2030

unknown

Some legacy tool

–

Not in PAM

(With "today" = 7 Oct 2026 and the PAM export of the same day.)

Risk levels: critical = out of maintenance · high = mainstream maintenance already ended · medium = ends within the warning window (default 12 months) · low = later · unknown = no date published or no confident match.

Get the data

Log in to the SAP Support Portal, open the Product Availability Matrix and export it as CSV (semicolon-separated, about 1,500 product versions).

Web app

Static HTML/JavaScript, no backend, no build step. Files are in app/.

  • Run locally: open app/index.html in a browser and drop the CSV on it.

  • Deploy to SAP BTP (Cloud Foundry):

cd app
cf login --sso
cf push

manifest.yml uses the static-file buildpack with 64 MB memory. The page stores the uploaded data in the visitor's own browser only.

Bundle the data for colleagues without an S-user (internal use): whoever has an S-user exports PAM once a month and runs:

npm run publish-data -- "C:\path\to\extractPAM.csv"
cd app
cf push

Visitors then see the data immediately, without uploading anything. The previous bundled export is kept, so What changed shows the month-to-month differences. A banner shows the export date and asks for a newer export after 30 days. app/data/ is git-ignored, so the data goes to your BTP app, never to GitHub.

⚠ A Cloud Foundry route is reachable by anyone who has the link. Bundled PAM data comes from behind an S-user login, so protect the app (e.g. approuter + XSUAA) before sharing it beyond a proof of concept, and check that sharing PAM content fits your SAP agreement. The page asks search engines not to index it, but that is not access control.

MCP server

Requires Node.js 18 or newer.

npm install
npm run convert -- "C:\path\to\extractPAM.csv"
npm test

Tool

Example question

pam_summary

"Give me an overview of SAP support status. How much ends in the next 6 months?"

pam_search_products

"When does support for Solman 7.2 end?"

pam_get_product

"Show me everything PAM says about SAP NETWEAVER 7.5."

pam_expiring

"Which Technology Platform products lose mainstream maintenance within 12 months?"

pam_check_landscape

"Here's our system list. Rate each system's support risk and what to upgrade to."

pam_upgrade_options

"We run BOBJ 4.3. What should we move to, and how long is that supported?"

pam_changes

"What did SAP change in PAM since last month that affects ECC6 ehp8, NW 7.5 and ASE 16.0.4?"

Comparing exports: each npm run convert of a newer export keeps the current data as data/pam-previous.json. To compare with an older export you already have:

npm run convert -- "C:\path\to\older-export.csv" --as-previous

Connect to Claude Desktop: quit Claude Desktop completely, then run npm run add-to-claude-desktop, then start Claude Desktop again. Or add this to claude_desktop_config.json yourself:

{
  "mcpServers": {
    "sap-pam": {
      "command": "node",
      "args": ["C:/path/to/pam-mcp-server/src/server.js"]
    }
  }
}

Limitations

  • Data is as fresh as your export. Re-export regularly; PAM online is always the reference.

  • Product dependencies are not modelled. For example, extended maintenance for Solution Manager comes from the ERP contract.

  • Upgrade paths are a starting point, not a migration plan. They do not check technical prerequisites, add-on compatibility or licensing.

  • Change detection needs two exports. It shows what changed between them, not when SAP made the change.

  • Empty dates are "unknown", never "no risk". About 7% of product versions have no end-of-mainstream-maintenance date in PAM.

  • Not affiliated with or endorsed by SAP.

Credits

Inspired by Tobias Hofmann's SAP Product Support Validation app and MCP server, shared on LinkedIn. This project builds on that idea with upgrade paths, export comparison and forgiving landscape matching; it is meant as a complement, not a replacement. The discussion under his post (product dependencies, matching against what is really running) shaped the roadmap.

License

MIT

Available Tools

7 tools
pam_changesWhat changed between PAM exportsA

Compare the current PAM export with the previous one: products newly listed or no longer listed, maintenance dates extended or shortened, status changes. Changes that need attention (shortened dates, removed dates, status now in customer-specific/extended/out of maintenance) come first. Optionally focus on a list of systems.

Inputs: limit, systems, onlyNeedsAttention.

pam_check_landscapeCheck a system landscapeA

Check a list of SAP systems/components (free text, e.g. from a design document or system list) against PAM. Matches each to a product version, rates support risk (critical, high, medium, low or unknown) and gives upgrade options (newer version of the same product, announced versions, SAP's strategic successor). Fuzzy matches should be confirmed by a person.

Inputs: systems (required), warnMonths.

pam_expiringProducts running out of supportA

List SAP product versions whose end of mainstream maintenance falls within the next N months, soonest first.

Inputs: limit, months, category, includeAlreadyEnded.

pam_get_productGet one product versionA

Full PAM record for one product version (exact name as in PAM, e.g. 'SAP NETWEAVER 7.5'), including all availability and maintenance dates and the Support Portal link. Suggests close names if not found.

Inputs: productVersion (required).

pam_search_productsSearch SAP productsA

Search SAP product versions in PAM by name (tolerant of shorthand like 'ECC EHP8', 'SolMan 7.2', 'BO 4.3'). Returns support dates, status and a risk assessment.

Inputs: limit, query, status, category.

pam_summaryPAM overviewB

Overview of the SAP Product Availability Matrix data: export date, number of product versions, counts by support status and category, and how many reach end of mainstream maintenance in 3/6/12/24 months.

Inputs: category.

pam_upgrade_optionsUpgrade options for a productA

What to move to from a given SAP product version: the newest released version of the same product with longer mainstream maintenance, any announced (not yet available) version, and SAP's strategic successor product where one exists (e.g. SAP ERP -> SAP S/4HANA). Accepts shorthand like 'ECC6 ehp7' or 'BOBJ 4.3'.

Inputs: product (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes (expiring list, summary stats, search, single-record fetch, landscape audit, upgrade paths, changelog). However, pam_search_products and pam_get_product both return product details at different depths, and pam_expiring overlaps conceptually with pam_summary's time-window counts, so a couple of boundaries need care.

    Naming Consistency4/5

    All tools share the consistent 'pam_' prefix, which is a strong plus. The second segment mixes noun-style names (pam_summary, pam_changes, pam_upgrade_options) with verb_noun patterns (pam_search_products, pam_get_product, pam_check_landscape), but everything remains readable and predictable.

    Tool Count5/5

    Seven tools is a well-scoped set for a read-only PAM query surface. Each tool covers a distinct query mode (time-based, aggregate, search, detail, batch audit, upgrades, change diff) and none feels redundant.

    Completeness4/5

    The surface covers the key PAM workflows: discovery by name, detail lookup, expiry tracking, summary metrics, landscape auditing, upgrade guidance, and export diffing. A minor gap is the lack of a browse/enumerate tool (e.g. list all products or filter by category/status) without knowing a product name in advance.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI clients to query live data from SAP HANA and SQL databases through read-only SELECT queries with CSV-formatted results.
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      AI-first CSV analysis tool that enables AI agents to analyze, query, and audit large CSV files directly within conversations, turning raw data into actionable insights.
      2
      -
    • F
      license
      B
      quality
      D
      maintenance
      Enables Claude to directly access, query, and analyze local CSV files using natural language, keeping data private and local.
      4
      1
      -