Skip to main content
Glama
Oracle Forms MCP

Oracle Forms MCP

by aoreshkov

Oracle Forms MCP

CI CodeQL Release License Kotlin

An MCP server that serves the content of Oracle Forms modules (.fmb forms, .mmb menus, .pll PL/SQL libraries, .olb object libraries) found in a directory, so AI assistants can inspect blocks, items, triggers, program units, and raw object XML without opening Forms Builder.

Built as a Kotlin Multiplatform core (pure @Serializable models and ports) with a JVM MCP server on top: declarative tool adapters over a single FormsService, stdio and HTTP transports, and a fingerprint-based on-disk cache. Oracle tool conversion feeds a streaming StAX parser that turns Forms XML into a structured index.

Why

Oracle Forms applications from the 1990s–2000s are still running critical business processes, but their logic is locked inside binary .fmb/.pll modules that only Forms Builder can open. That makes them opaque to modern AI tooling and painful to review, document, or migrate.

Oracle Forms MCP turns those modules into structured, queryable content so an AI assistant can:

  • Understand a legacy app — enumerate blocks, items, triggers, and program units without a Forms IDE.

  • Review & document PL/SQL — pull decoded trigger and program-unit bodies straight into the model's context.

  • Assist modernization — feed decades-old business logic to an assistant for migration to APEX, Java, or a rewrite, and search across every module's source.

  • Capture & retain knowledge — let the assistant record notes, tags, and cross-references on individual elements that persist across sessions and re-indexing, building up a durable map of a form no one fully remembers.

It is aimed at developers and teams doing Oracle Forms modernization, reverse engineering, code review, and documentation — anyone who needs to read Forms logic faster than opening it by hand.

Related MCP server: apex-mcp

See it work

A typical session against the bundled sample-forms directory:

You:  What does ORDERS.fmb do?
AI →  list_modules                 → ORDERS.fmb (NOT_CACHED), MAINMENU.mmb, UTILS.pll …
AI →  fetch_module ORDERS.fmb      → converted + indexed (3 blocks, 3 triggers, 3 program units)
AI →  get_module_overview ORDERS   → blocks, triggers, LOVs, record groups, windows, canvases …
You:  Show me the validation logic on the ORDERS block.
AI →  list_triggers block=ORDERS   → WHEN-VALIDATE-ITEM (on ORDER_ID), WHEN-VALIDATE-RECORD
AI →  get_trigger ORDERS WHEN-VALIDATE-ITEM  → the decoded PL/SQL body
You:  Where else is the CALC_TOTAL procedure called?
AI →  search_source "calc_total" scope=plsql  → hits across triggers and program units
You:  That validation is the legacy pre-2010 path — note it so we remember.
AI →  annotate_element ORDERS trigger WHEN-VALIDATE-ITEM kind=note "Legacy pre-2010 validation path" → saved
      (next session)  get_trigger ORDERS WHEN-VALIDATE-ITEM → body + the stored note inline

How it works

list_modules scans the directory you name and reports each module's cache status. fetch_module produces the module's text form, with the Oracle tools when ORACLE_HOME is set and from pre-converted files next to the modules when it is not, and parses it into a structured index. The other tools read that index. A STALE module is one whose source changed or whose index an older build wrote, and fetching it again clears that. Notes recorded with annotate_element and relate_elements live in a separate store, so re-fetching keeps them.

How it works has the full sequence and the cache layout.

Tools

Tool

What it does

list_modules

Modules in the forms dir with type, size, and cache status; filter by pattern/regex, type, status and page via limit/cursor

fetch_module

Converts + indexes one module (idempotent; force=true converts a current one again; progress notifications)

get_module_overview

Names of every section + counts — the first call after a fetch (verbosity=detailed adds window and canvas objects)

list_blocks

Blocks with base table, item count, trigger count

get_block

One block: items with type, property class, prompt and trigger names, and its master-detail relations (verbosity=detailed adds data type, column, canvas, size, visible/required/LOV and the DML properties resolved through each item's property class; columns=true adds the base table's columns and the ones no item supplies); flags subclassed blocks/items

list_triggers

Triggers with level/scope; filter by block, item, or level (verbosity=detailed adds a PL/SQL preview)

get_trigger

One trigger's decoded PL/SQL body (same-named triggers told apart by ownerPath or level); resolve follows a subclassing pointer into a cached parent module

list_program_units

Procedures, functions, package specs/bodies with line counts

get_program_unit

One program unit's PL/SQL (disambiguate spec/body via unitType); resolve as for get_trigger

search_source

Line search over one fetched module: extracted PL/SQL (plsql), the raw XML (xml), or both; paginated via offset/nextOffset

search_modules

The same search across every cached module — cross-form calls, shared :GLOBALs, subclassing pointers; reports the modules it could not reach; paged via an opaque cursor

read_source

A line range of a cached file, by uri (which names its module) or module + file — the converted XML or an extracted PL/SQL sidecar

get_object_xml

The raw XML fragment of any named object — the escape hatch

annotate_element

Store a note / summary / tag / classification about one element

relate_elements

Record a directed cross-reference between two elements (e.g. a trigger calls a program unit)

get_element_annotations

The notes and relations stored about one element

search_annotations

Search a module's stored notes/tags/relations by text, kind, or tag

remove_annotation

Delete a stored annotation or relation by id

Every tool checks its arguments against its own input schema before running. An argument it does not have is never silently dropped: the call fails with every problem listed at once (unknown arguments with the name most likely meant, missing ones with their permitted values, values outside an enum), plus an example call where the tool has one.

The server also offers a resource per cached module (oracleforms://ORDERS.fmb/index), the oracleforms://{module}/index and oracleforms://{module}/annotations resource templates, and an explain_module prompt.

Tools in depth explains how to read the results: property classes, source references, subclassed objects, tracing across modules, and annotations.

Quick start

Pick the channel that matches your client: the plugin for Claude Code, the .mcpb bundle for Claude Desktop, the Docker image for other MCP clients, or a build from source. The server is published to the official MCP Registry as io.github.aoreshkov/oracle-forms-mcp.

Claude Code (one-command plugin)

/plugin marketplace add aoreshkov/oracle-forms-mcp
/plugin install oracle-forms@oracle-forms-mcp

Claude Code prompts for your forms directory, then fetches and checksum-verifies the released server into the plugin's data directory on first use — no clone, no build, no JSON to edit. The tools are live after /reload-plugins, and the plugin's trace-form skill teaches the traversal — the order to ask in, and the readings that mislead — so a trace does not start with grep. Skip the prompt and the server still starts; its tools then answer with an error asking for the directory until you set it with /plugin configure oracle-forms@oracle-forms-mcp.

IMPORTANT

Requires a JDK 25+ (javac -version), because the plugin's bootstrap runs in Java's single-file source mode. It uses the one on your PATH unless you set the plugin's java option to another JDK's java executable, and falls back to JAVA_HOME when that one is too old for the server. With only a JRE, use the .mcpb bundle or claude mcp add below.

Details, configuration options, and the escape hatches are in the plugin README.

Claude Desktop (one-click bundle)

Download oracle-forms-mcp-<version>.mcpb from the latest release and open it. Claude Desktop installs it as a connector and prompts for your forms directory with a native folder picker — no JSON editing, no local build. Leave it empty and the connector still starts; its tools then answer with an error asking for the directory until you set it in the connector's settings.

IMPORTANT

Requires a JRE 25+. The bundle ships the server, not a Java runtime. It runs on the Java installation chosen in the connector's settings, else the one JAVA_HOME names, else the java on your PATH. The MCPB manifest format can only declare Node and Python runtimes, so this cannot be checked at install time: if the connector fails to start, choose the Java installation in its settings, or confirm java -version works in a terminal.

The same copy-mode caveat as Docker applies unless the machine has an Oracle Forms installation (ORACLE_HOME) for live .fmb/.pll conversion.

Build from source

Building works from any JDK 17+ that can start the wrapper (Gradle downloads JDK 25 for its daemon and the toolchain when none is installed). Running needs a JRE 25+. Build and install:

gradlew :server:installDist

Register with Claude Code (stdio):

claude mcp add oracle-forms -- server/build/install/server/bin/server --forms-dir C:\path\to\forms

The server script runs on the Java installation OFMCP_JAVA_HOME names, else JAVA_HOME, else the java on PATH, so a JRE that is not on PATH is one variable away:

claude mcp add --env OFMCP_JAVA_HOME=C:\Java\jdk-25 --transport stdio oracle-forms -- server/build/install/server/bin/server --forms-dir C:\path\to\forms

Try it without any Oracle installation using the bundled fixtures:

server --forms-dir sample-forms

Using your own converter

If your site wraps the Forms tools or uses a different converter, --convert-command runs it in place of frmf2xml, and --compile-command does the same for .pll libraries. The converters guide has the command syntax, the placeholders and the precedence.

Documentation

Page

What it covers

Installing

Other MCP clients, the HTTP transport, Docker

Configuration

Command-line options and environment variables

Converters

Keeping the converted XML, your own converter, PL/SQL libraries, notes on the Oracle tools

How it works

The fetch-and-index sequence and the cache layout

Tools in depth

How to read tool results, subclassed objects, tracing across modules, annotations

Claude Code plugin

Plugin options, how the server is delivered, escape hatches

Changelog

What changed in each release

Privacy Policy

Oracle Forms MCP runs entirely on your machine and collects nothing.

  • Data collection. None. The server has no telemetry, analytics, crash reporting, or accounts, and it makes no network requests of its own.

  • What it reads and stores. It reads the modules in the --forms-dir you name and writes derived files — converted text forms, decoded PL/SQL, and index.json — to the local cache (or --converted-dir). Annotations you or your assistant record are written to the local annotations store. All of these stay on your disk, and you can delete them at any time.

  • Where content goes. Module content leaves the server only as responses to the MCP client you connected it to. What that client does with it — including sending it to a model provider — is governed by that client's own privacy policy, not this one. The http transport listens on 127.0.0.1 only unless you bind it elsewhere with --host.

  • Third-party sharing. None. The one exception to "no network" is the Claude Code plugin's launcher: it asks the GitHub API for the latest release at most once a day and downloads the release zip and its checksum from GitHub Releases. Those requests go to GitHub, under GitHub's privacy statement, and carry nothing from your modules. Pin server_version or use OFMCP_SERVER_HOME to avoid them.

  • Retention. Cached and annotation files persist until you delete them; the software keeps nothing anywhere else.

  • Contact. Questions go to GitHub issues; security reports follow SECURITY.md.

Help

Ask questions in Discussions, and report bugs or request features in issues. Security reports follow SECURITY.md.

Contributing

CONTRIBUTING.md covers building, testing and sending a change.

License

Apache License 2.0. See LICENSE and NOTICE.

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides contextual Oracle database schema information to AI assistants, enabling them to understand and work with large databases containing thousands of tables. Supports multi-database connections, smart schema caching, table lookups, and relationship mapping.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to safely inspect Oracle Database schemas, objects, and PL/SQL source with a strict read-only guard, without ever modifying data.
      16 npm
      MIT