SAP SuccessFactors

io.github.wudaoyouPublished by GitHub account wudaoyouv0.7.0Updated Oct 24, 2026

SAP SuccessFactors OData and Compound Employee queries with PII tokenization for AI agents.

VerifiedSTDIODesktop onlyDatabasesDeveloper ToolsBusiness & Commerce

Overview

AI-generated overview

A self-hosted Docker MCP server that lets an AI assistant query SAP SuccessFactors OData and Compound Employee APIs, with PII tokenization and local exports.

What you can do
Query SuccessFactors OData v2 and v4 services through execute, extract and filter-based operations, with per-request connection overrides and documented API pitfalls handled by the toolkit. Look up and filter Employee Central Compound Employee data over SOAP, including pagination. Tokenize PII in payloads and export results in supported formats such as CSV. Write results to a local data directory for review or copying to an authorized folder. Extend behavior through plugins.
When to use it
Useful for functional consultants, business key users and integration developers who need an AI assistant to troubleshoot SuccessFactors APIs, pull employee payloads, or prototype integrations against a tenant. Best when HR data must stay on a controlled local machine.
Requirements
Docker Desktop or an IT-managed Docker service running the published image over stdio. One-time Docker Compose setup and approved connection files, one folder per SuccessFactors system under the credentials directory, including generated key pairs. Network access to the configured SuccessFactors tenant. A file-capable AI application for CSV conversion.
Before you install
It connects to a live SuccessFactors tenant and queries real employee data. Credentials, certificates, tenant exports and employee payloads must stay out of Git; the repository's guardrails are not a complete secret or PII scanner. A local agent calling a cloud model may send prompts, tool responses and file contents off the machine, so use a locally hosted model if HR data must stay in your environment. Prefer local deployment over hosted MCP services.

Installation

In SourceWeft

  1. Open SAP SuccessFactors in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

SuccessFactors Toolkit

[CI] [License] [Python]

A self-hosted toolkit for SAP SuccessFactors API troubleshooting, payload extraction, and integration development, exposed as a REST API and as an MCP (Model Context Protocol) server.

APIProtocolEndpoint prefix
EC SFAPI — Compound EmployeeSOAP 1.1/api/sfapi/ce/
ODataREST (v2, v4)/api/odata/

OData v4 covers the SuccessFactors APIs published as v4 services (for example Calibration and Continuous Feedback); Employee Central and Onboarding data stay on v2. See OData API.

This is an independent project, not affiliated with or endorsed by SAP SE. SAP and SuccessFactors are trademarks of SAP SE.

Start here: Docker MCP → credentials → ask → export

Data security: prefer local deployment. For sensitive SuccessFactors employee data and credentials, we recommend running the MCP server in local Docker and using a local AI agent, rather than an online AI platform or a third-party hosted MCP service. Keep credentials and exports on your machine; do not upload private keys or employee payloads to online platforms.

A local AI agent is not necessarily a local model. If it calls a cloud model, prompts, tool responses, previews, and file contents supplied to that model may leave your machine. If HR data must stay within your controlled environment, use a locally hosted model and local file-processing tools, and check the agent's outbound data handling. Local Docker alone does not guarantee this. The toolkit still connects to your configured SuccessFactors tenant to query data.

For functional consultants and business key users, start with the business user guide or its English/Chinese HTML edition. Ask IT to complete the one-time Docker Compose setup and provide approved connection files. Then:

  1. Check Docker Desktop or your IT-managed Docker service is running, then open your local AI application.
  2. Confirm with IT that the connection files are in sf-toolkit/credentials/systems, one folder per SuccessFactors system.
  3. Confirm which SuccessFactors system to use and ask for the employee, date, and information you need.
  4. Find results under sf-toolkit/data/mcp. Ask a file-capable AI application for CSV or another supported format, or a copy in an authorized folder.

The guide includes example business questions, completion checks, troubleshooting, and expandable one-time settings for your administrator. Original OData results are JSON; Compound Employee results are XML. CSV conversion requires local file tools in the AI application.

Documentation

PageCovers
REST APIFail-closed setup, install and run, cheat sheet, response format
Connect to SuccessFactorsKey pair generation, system files (SYSTEMS_DIR/<name>/<name>.json), environment variables, system management
EC SFAPI (SOAP)Compound Employee single lookup, structured filter query, pagination, known footguns
OData APIexecute / extract / extract-by-filter-in, OData v4 services, per-request connection override, known API footguns
MCP serverTools for AI agents, payload handling, export formats, PII tokenization, plugins
DevelopmentLocal dev setup, linting, tests, release process

Data handling

Use synthetic examples and test fixtures. Credentials, certificates, tenant exports, employee payloads, and generated results do not belong in Git — .gitignore and scripts/check_repository.py are a basic guardrail, not a complete secret or personal-data scanner. See SECURITY.md for deployment guidance and how to report a vulnerability.

License

Apache License 2.0. Copyright 2026 Justin Gong. See NOTICE for third-party and migrated-code attribution.

Source: README.md at commit db32da4

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the package type cannot run in the sandbox.

Version history

7
  1. v0.7.0LatestOct 24, 2026
  2. v0.6.0Oct 6, 2026
  3. v0.5.5Oct 3, 2026
  4. v0.5.4Oct 2, 2026
  5. v0.5.2Sep 30, 2026
  6. v0.5.0Sep 29, 2026
  7. v0.4.1Sep 29, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts