Maven Decoder MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAVEN_HOME | No | Custom Maven repository location | ~/.m2/repository |
| MCP_LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR) | INFO |
| MCP_MAX_LINES | No | Maximum lines before summarization | 500 |
| MCP_MAX_TEXT_LENGTH | No | Maximum text length before summarization | 10000 |
| MCP_MAX_RESPONSE_SIZE | No | Maximum response size in bytes | 50000 |
| MCP_MAX_ITEMS_PER_PAGE | No | Default items per page | 20 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_artifactsA | List all Maven artifacts in the local repository with optional filtering |
| analyze_jarC | Analyze a specific jar file and extract detailed information |
| extract_class_infoC | Get detailed information about Java classes in a jar |
| get_dependenciesC | Get Maven dependencies from POM files |
| search_classesC | Search for Java classes across all jars in the repository |
| extract_source_codeB | Extract source code from jar (if available) or decompile bytecode |
| extract_jar_resourceA | Extract text resources from a jar, such as .proto files, service descriptors, or metadata |
| compare_versionsA | Compare different versions of the same Maven artifact |
| find_usage_examplesB | Find usage examples of classes/methods in test jars |
| get_dependency_treeC | Get complete dependency tree for an artifact |
| find_dependentsC | Find artifacts that depend on a specific artifact |
| get_version_infoB | Get all available versions of an artifact, optionally including versions published remotely |
| analyze_jar_structureC | Analyze the overall structure and metadata of a jar file |
| extract_method_infoC | Extract specific method information from a Java class |
| search_maven_centralA | Search Maven Central (or the configured mirror) online for artifacts, including ones not installed locally. Use this to discover coordinates or find which published artifact contains a class. |
| get_remote_versionsA | List all versions of an artifact published on the remote repository, including versions that are not installed locally |
| download_artifactA | Download an artifact from the remote repository into the local analysis cache so every other tool can inspect it. Use 'latest' as the version to fetch the newest release. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 17 tools
Several tools have overlapping purposes—analyze_jar_structure vs analyze_jar, get_version_info vs get_remote_versions, get_dependencies vs get_dependency_tree, and search_classes vs search_maven_central—so an agent could easily pick the wrong one. The descriptions clarify local vs remote or detail level somewhat, but the boundaries are not crisp.
All tool names follow a consistent lowercase snake_case verb_noun pattern, using verbs like analyze, list, extract, get, search, compare, find, and download. The naming makes the action and target clear even when some tools are semantically close.
17 tools is slightly above the ideal 3-15 range, but the server covers a broad domain: local repository scanning, jar inspection, dependency analysis, remote search, and downloading. A few redundant tools could be consolidated, but the count is not excessive.
The tool set covers artifact discovery, downloading, jar analysis, class/method/source extraction, dependency trees, reverse dependents, and remote version lookup. This is a comprehensive read/analysis surface with no obvious dead-end gaps for the stated Maven decoder purpose.