Agendum
by srallicommunityv0.3.4
6
agendum is an MCP server for AI coding agents that adds persistent project memory, scoped work packages, dependency tracking, and cross-session continuity. It stores project state in human-readable Markdown/YAML files and exposes tools to plan, ingest, track, and complete tasks.
From the registry: AI agent memory: task tracking, scoped work packages, decisions, and cross-session continuity
Install & configure
Prerequisites
- required
- requiredInstall uvx or install agendum via pipThe recommended MCP config uses uvx to run agendum. Alternatively, you can install the package with pip for CLI use.
https://pypi.org/project/agendum/$ pip install agendum
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `agendum` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.13+** — agendum requires Python 3.13 or newer. (https://www.python.org/downloads/)
- **Install uvx or install agendum via pip** — The recommended MCP config uses uvx to run agendum. Alternatively, you can install the package with pip for CLI use. Run: `pip install agendum` (https://pypi.org/project/agendum/)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["agendum","--home","serve"]
Note: README states all MCP clients except VS Code use the same underlying stdio command/args. No environment variables are documented as required for the MCP server. Optional vector search is mentioned via agendum[vectors], but it is not required for the default MCP setup.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: README states all MCP clients except VS Code use the same underlying stdio command/args. No environment variables are documented as required for the MCP server. Optional vector search is mentioned via agendum[vectors], but it is not required for the default MCP setup.
Tools (14)
pm_init
Initialize the board directory, optionally on first use
pm_project
Create, list, or get projects
pm_status
Show dashboard info including item counts, progress, memory health, and suggested next task
pm_add
Add a board item with type, priority, tags, dependencies, and acceptance criteria
pm_board
View and filter the project board
pm_ingest
Import a Markdown plan file into board items with dependencies
pm_next
Get the next scoped work package with context and complexity signal
pm_done
Mark an item complete and record decisions, patterns, and learnings; can auto-extract git info and unblock dependents
pm_block
Report a task as blocked with a reason
pm_memory
Read, write, append, or search project memory
pm_learn
Record global or project-scoped learnings with tags and entities
pm_search
Search across memory, learnings, and completed items
pm_consolidate
Clean memory corruption, deduplicate learnings, and detect contradictions
Prerequisites
- • Python 3.13+
Packages
agendum
pypiv0.3.4transport: stdio
Details
- Language
- Python
- License
- MIT
- Released
- Apr 13, 2026
- Last commit
- Apr 13, 2026
- Registry name
- io.github.sralli/agendum
Related Servers
Claude Flow
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
68.0k
Codebase Memory Mcp
Persistent codebase knowledge graph. Survives session restarts and context compaction.
39.2k
Serena
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
28.1k