MCP Memory Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROJECT_ROOT | Yes | The path to your project directory where the MCP memory server will store data and track files |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_sessionC | Start a new AI coding session with a specific task |
| add_session_stepC | Record completion of a step in the current session |
| add_decisionC | Record an important technical decision |
| get_project_memoryB | Get current project memory and session state |
| set_file_approvalC | Set approval status for a file |
| get_file_approval_statusC | Get approval status for a file |
| check_before_modificationC | Check if a file can be modified according to AI metadata rules |
| get_modification_actionsC | Get actions that should be taken after modifying a file |
| parse_file_metadataC | Parse AI metadata from a file |
| update_file_metadataC | Update AI metadata in a file |
| find_files_with_metadataC | Find all files that contain AI metadata |
| add_changelog_entryC | Add an entry to the project changelog |
| get_file_changelogC | Get changelog entries for a specific file |
| get_recent_changesC | Get recent changelog entries |
| generate_folder_mapC | Generate or update a _map.md file for a specific folder |
| generate_all_folder_mapsB | Generate _map.md files for all folders in the project |
| update_last_editorC | Update @last-editor field in a file with Git author information |
| update_all_last_editorsB | Update @last-editor fields in all files with Git author information |
| get_file_last_editorC | Get the last editor of a file from Git history |
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 19 tools
Most tools have distinct purposes, but there is some overlap between 'update_file_metadata' and 'parse_file_metadata' that could cause confusion, as both involve metadata handling. Additionally, 'get_file_last_editor' and 'update_last_editor' are closely related but serve different functions, which is acceptable. Overall, the tools are well-differentiated with only minor ambiguities.
The tool names follow a consistent verb_noun pattern throughout, such as 'add_changelog_entry', 'find_files_with_metadata', and 'update_file_metadata'. All tools use snake_case without deviation, making the naming highly predictable and readable. This consistency aids in easy identification and usage by agents.
With 19 tools, the count is slightly high but reasonable for a memory server that manages project metadata, changelogs, and sessions. The tools cover various aspects like file operations, session management, and metadata handling, so each seems to earn its place. However, it borders on being heavy, which could overwhelm agents if not well-organized.
The tool set provides comprehensive coverage for project memory management, including CRUD operations for metadata, changelogs, and approvals, as well as session lifecycle management. Tools like 'start_session', 'add_session_step', and 'get_project_memory' ensure full session handling, while others cover file-specific actions and metadata updates, leaving no obvious gaps for the domain.