peoplesoft-mcp: Skill for Cursor

.cursor/skills/peopletools-mcp/SKILL.md

peopletools-mcp is a skill for Cursor from rgrz/peoplesoft-mcp. It costs 53 tokens per session (977 once invoked), scanned A, original, MIT.

A guide for using and extending an MCP server that connects agents to PeopleSoft databases and metadata. PeopleSoft is enterprise software that stores business records and workflows; the guide covers record definitions, PeopleCode, and database queries.

In plain words
What is it for?
Use it to inspect PeopleSoft record structures, read PeopleCode, query PeopleSoft data, describe metadata tables, and investigate application components.
Why use it?
PeopleTools versions can expose different metadata fields, so some specialized inspection tools may fail. The guide gives reliable tools first and database-query fallbacks for exploring components.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is rgrz/peoplesoft-mcp's own configuration. It tells Cursor how to work on peoplesoft-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything peoplesoft-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rgrz/peoplesoft-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rgrz/peoplesoft-mcp/main/.cursor/skills/peopletools-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rgrz/peoplesoft-mcp

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for peopletools-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/rgrz/peoplesoft-mcp/peopletools-mcp/github.svg)](https://agentmods.dev/skills/rgrz/peoplesoft-mcp/peopletools-mcp)
Your own site
<a href="https://agentmods.dev/skills/rgrz/peoplesoft-mcp/peopletools-mcp"><img src="https://agentmods.dev/badge/skills/rgrz/peoplesoft-mcp/peopletools-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for peopletools-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/rgrz/peoplesoft-mcp/peopletools-mcp"><img src="https://agentmods.dev/badge/skills/rgrz/peoplesoft-mcp/peopletools-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 977 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00977
Opus 5 $0.00026 $0.00489
Sonnet 5 $0.00011 $0.00195
Haiku 4.5 $0.00005 $0.00098

Measured 11d ago against content hash 58eeecd85c7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

peopletools-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/peopletools-mcp/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PeopleTools MCP

Guide for using the PeopleSoft MCP server and proposing enhancements. MCP tools live in tools/peopletools.py; the server is peoplesoft_server.py.

Tool Selection

Reliable (use first):

  • get_record_definition(record_name) — fields, keys, types
  • get_peoplecode(record_name, field_name?, event?, include_code?) — PeopleCode from PSPCMTXT
  • query_peoplesoft_db(sql_query, parameters?) — raw SQL fallback
  • describe_table(table_name) — field list for metadata tables

May fail (PeopleTools version differences): get_component_structure, get_page_fields, get_application_engine_steps reference columns that vary by PT version (SAVEWARN, ITEMNUM vs SUBITEMNUM, AE_STEP_NBR vs AE_SEQ_NUM, DSPCTLFLDNAME, etc.).

Fallback: When a semantic tool errors, use query_peoplesoft_db with describe_table first to confirm column names. Proven patterns in reference.md.

Component Exploration Workflow

For a component (e.g., ABSV_REQUEST):

  1. Record: get_record_definition("ABSV_REQUEST")
  2. PeopleCode: get_peoplecode("ABSV_REQUEST")
  3. Component/Pages: If get_component_structure fails, use:
SELECT PNLGRPNAME, DESCR, SEARCHRECNAME FROM PSPNLGRPDEFN WHERE PNLGRPNAME = 'ABSV_REQUEST';
SELECT PNLNAME, SUBITEMNUM, ITEMLABEL FROM PSPNLGROUP WHERE PNLGRPNAME = 'ABSV_REQUEST' ORDER BY SUBITEMNUM;
  1. Page fields: If get_page_fields fails:
SELECT RECNAME, FIELDNAME, FIELDNUM FROM PSPNLFIELD WHERE PNLNAME = 'ABSV_REQUEST' ORDER BY FIELDNUM;

MCP Resources

Use fetch_mcp_resource with user-peoplesoft for:

  • peoplesoft://peopletools-guide — records, pages, PeopleCode events, security, AE, IB
  • peoplesoft://schema-guide — tables by module (HR, Payroll, Benefits, etc.)
  • peoplesoft://concepts — effective dating, EMPLID, SetID
  • peoplesoft://query-examples — SQL patterns with effective dating

Proposing Enhancements

When a tool fails or a new capability would help:

  1. Identify the metadata tables — See peopletools-tables-by-tool.md
  2. Check schema — Use describe_table("PSPNLGRPDEFN") (or target table) to verify column names
  3. Minimize column dependencies — Prefer widely available columns; avoid SAVEWARN, DSPCTLFLDNAME, AE_STEP_NBR, ITEMNUM
  4. Add to tools/peopletools.py — Follow existing patterns (normalize record names, handle LOBs via DBMS_LOB)
  5. Register in register_tools() — Add mcp.tool()(new_function)

Read the full file on GitHub · 82 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 82 lines · 53 tokens per session scan A 58eeecd85c7b

Subscribe to this mod's changes

peopletools-mcp is a skill published in the GitHub repository rgrz/peoplesoft-mcp (12 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 977 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens

convex-explain-app

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

openclaw/clawhub · 47 tokens

platform-custom-field-generate

Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…

forcedotcom/sf-skills · 194 tokens

durable-objects

Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

fcakyon/claude-codex-settings · 22 tokens

field-service-sobject-create-configure

Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…

forcedotcom/sf-skills · 74 tokens

nornicdb-grpc

Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…

orneryd/NornicDB · 98 tokens