Agendum MCP server
✓ VerifiedProvides AI agents with persistent project memory, task tracking, and bounded work packages to maintain continuity across sessions.
Also known as sralli/agendum
- Stars
- 6
- Tools
- 14
- Downloads, 30 days
- 103
- Latest version
- 0.3.4
- Last commit
- Apr 13, 2026
- License
- MIT
What is Agendum MCP?
Agendum provides AI agents with persistent project memory, task tracking, and bounded work packages to maintain continuity across sessions. It exposes 14 tools, such as pm_init, pm_project, pm_status.
Summary generated from the project's README
About Agendum MCP server
Maintaining continuity for AI coding agents during complex development cycles is what Agendum enables. It provides a persistent memory and scoping engine that prevents stateless agents from forgetting decisions or losing context between sessions. By using this MCP server with clients like Claude Code, Cursor, Windsurf, or Cline, developers can transform an agent from a tool that modifies random files into one that operates within bounded work packages containing specific acceptance criteria and constraints.
The system manages a dependency graph to order tasks and automatically unblock items as work is completed. It uses a variety of tools including pm_ingest to import Markdown plans, pm_next to retrieve the next scoped task, and pm_done to record decisions and patterns. All project state is stored in human-readable Markdown and YAML files, making the memory diffable and committable via Git. The server also features a hybrid search capability that combines keyword matching, vector search, and an entity graph to surface relevant project knowledge.
Written from the project's README. Every use case is checked against a quote from it.
How to install Agendum MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Agendum MCP in Claude Code
$ claude mcp add agendum -- uvx agendumInstall Agendum MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agendum": {
"command": "uvx",
"args": [
"agendum"
]
}
}
}Install Agendum MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agendum": {
"type": "stdio",
"command": "uvx",
"args": [
"agendum"
]
}
}
}Install Agendum MCP in VS Code CLI
$ code --add-mcp '{"name":"agendum","type":"stdio","command":"uvx","args":["agendum"]}'Install Agendum MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agendum": {
"command": "uvx",
"args": [
"agendum"
]
}
}
}Install Agendum MCP in Codex
$ codex mcp add agendum -- uvx agendumInstall Agendum MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agendum] command = "uvx" args = ["agendum"]
Install Agendum MCP in Gemini CLI
$ gemini mcp add -s user agendum uvx -- agendumInstall Agendum MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agendum": {
"command": "uvx",
"args": [
"agendum"
]
}
}
}Agendum MCP tools 14
Detected from the READMEpm_initpm_projectpm_statuspm_addpm_boardpm_ingestpm_nextpm_donepm_blockpm_memorypm_learnpm_search
| pm_init | — | |
| pm_project | — | |
| pm_status | — | |
| pm_add | — | |
| pm_board | — | |
| pm_ingest | — | |
| pm_next | — | |
| pm_done | — | |
| pm_block | — | |
| pm_memory | — | |
| pm_learn | — | |
| pm_search | — |
Show all 14 toolsShow fewer tools
pm_consolidatepm_supersede
| pm_consolidate | — | |
| pm_supersede | — |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablesralli/agendum is public and reachablegithub.com/sralli/agendum ↗Pass
- Package names this repository as its sourceagendum names sralli/agendum as sourcepypi.org/project/agendum/ ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-04-13github.com/sralli/agendum ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from agendumPass
- No critical advisory in the package or its dependencies40 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model14 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubagendum
Project memory and scoping engine for AI coding agents.
AI coding agents are stateless — they forget between sessions, lose decisions, and have no way to scope complex work. agendum is an MCP server that gives any agent (Claude Code, Cursor, Windsurf, Cline, and others) persistent project state, bounded work packages, and cross-session continuity.
| Without agendum | With agendum |
|---|---|
| Agent forgets everything between sessions | Picks up exactly where it left off |
| No scope — agent modifies random files | Bounded work packages with file lists, acceptance criteria, constraints |
| Decisions lost — same mistakes repeated | Decisions and patterns persist in searchable memory |
| No task ordering — agent picks randomly | Dependency graph with auto-unblocking and priority scoring |
| Learning locked inside one project | Cross-project learnings carry patterns forward |
Quick Start
pip install agendum # or: uvx agendum
claude mcp add agendum -- uvx agendum --home serve # add to Claude Code
# Done. pm_* tools are now available in your agent.
Works with any MCP client — see setup for Cursor, Windsurf, VS Code, and others.
How It Works
flowchart LR
A["PLAN\nwrite plan file"] --> B["pm_ingest\nboard items + deps"]
B --> C["pm_next\nwork package + context"]
C --> D["EXECUTE\nagent implements"]
D --> E["pm_done\ndecisions + patterns"]
E -->|next task| C
E -->|new session| F["pm_status\nresume context"]
F --> C
Each pm_done records decisions and patterns that enrich future pm_next calls — context compounds across sessions.
Example session:
You: I have a plan file for the API rewrite. Ingest it.
Agent:
→ pm_ingest(project="api-rewrite", plan_file="plan.md")
Ingested 4 board items from plan:
item-001: Schema design [high]
item-002: Resolver layer (depends on item-001)
item-003: Auth middleware (depends on item-001)
item-004: Integration tests (depends on item-002, item-003)
You: What should I work on?
Agent:
→ pm_next(project="api-rewrite")
Work package for item-001 "Schema design":
Context: project rules, memory from last session
Scope: Define GraphQL schema types
Acceptance criteria: Types for User, Product, Order
You: Done with the schema. Here's what I decided...
Agent:
→ pm_done(project="api-rewrite", item_id="item-001",
decisions="Using code-first with Strawberry",
patterns="N+1 queries need DataLoader",
verified=True)
Marked item-001 as done. Unblocked: item-002, item-003
> Next: pm_next("api-rewrite") to continue with newly unblocked tasks
14 MCP Tools
Setup & Orientation
| Tool | Purpose |
|---|---|
pm_init |
Initialize board directory (optional — auto-initializes on first use) |
pm_project |
Create, list, or get projects |
pm_status |
Dashboard — item counts, recent progress, memory health, suggested next task |
Planning & Backlog
| Tool | Purpose |
|---|---|
pm_add |
Add an item with type, priority, tags, dependencies, acceptance criteria |
pm_board |
View and filter the project board |
pm_ingest |
Import a Markdown plan file into bounded board items with dependencies |
Execution Loop
| Tool | Purpose |
|---|---|
pm_next |
Get the next scoped work package with complexity signal and enriched context |
pm_done |
Complete an item — record decisions, patterns, learnings; auto-extract from git; auto-unblock dependents |
pm_block |
Report a task as blocked with reason |
Knowledge & Search
| Tool | Purpose |
|---|---|
pm_memory |
Read, write, append, or search project memory (decisions, patterns, project knowledge) |
pm_learn |
Record global or project-scoped learnings with tags and topic entities |
pm_search |
Hybrid search across all knowledge — memory, learnings, completed items |
pm_consolidate |
Clean memory corruption, deduplicate learnings, detect contradictions |
pm_supersede |
Soft-invalidate a learning — excluded from all future searches |
Hybrid Search
pm_search combines three signals to find relevant knowledge across memory, learnings, and completed board items:
- FTS5 with Porter stemming —
authmatchesauthentication,configmatchesconfiguration. Always on, zero config. - Vector search (optional) — Install
agendum[vectors]to add semantic similarity viafastembed+sqlite-vec. Activates automatically alongside FTS5. - Entity graph — Topics and tags form a knowledge graph. Entries sharing 2+ entities are linked automatically. Graph expansion surfaces related knowledge that keyword search misses.
All three signals are fused via Reciprocal Rank Fusion (RRF), then reranked by recency and access frequency. The index rebuilds from Markdown files — no data loss if it gets corrupted.
Key Capabilities
- Adaptive context budget — enrichment scales with task complexity: 4K chars for trivial tasks, up to 10K for large ones
- Verification gate —
pm_done(verified=True)distinguishes tested from untested completions - Git auto-extract —
pm_donereadsgit diffandgit logautomatically when no files are specified - Pluggable enrichment pipeline — four context sources injected into every work package: project rules (CLAUDE.md/AGENTS.md), memory, dependency context, learnings
- Dependency resolution — topological ordering with cycle detection; dependents unblock automatically when upstream tasks complete
- Memory health —
pm_statuswarns about corrupted entries;pm_consolidatestrips XML fragments, deduplicates, and flags contradictions - Zero config — auto-initializes on first tool call, derives board name from git remote
- Git-native storage — all state is human-readable Markdown + YAML in
.agendum/, diffable and committable
Installation
All MCP clients except VS Code use the same config. Add to the appropriate file:
{
"mcpServers": {
"agendum": {
"command": "uvx",
"args": ["agendum", "--home", "serve"]
}
}
}
| Client | Config location |
|---|---|
| Claude Code | Run: claude mcp add agendum -- uvx agendum --home serve |
| Cursor | .cursor/mcp.json in project root |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| Cline | Settings › MCP Servers › Edit |
| Roo Code | MCP settings file |
| Claude Desktop | claude_desktop_config.json |
VS Code (GitHub Copilot): Uses
"servers"instead of"mcpServers". Add to.vscode/mcp.json:{ "servers": { "agendum": { "command": "uvx", "args": ["agendum", "--home", "serve"] } } }
CLI (standalone)
pip install agendum
agendum project create my-app # Create a project
agendum status # Dashboard overview
agendum next my-app # Suggest next task
Storage Layout
All state lives in ~/.agendum/ (or .agendum/ in your project if you prefer local storage):
~/.agendum/
├── .cache/
│ └── search.db # FTS5 + vector search index (auto-rebuilt)
├── config.yaml
├── projects/
│ └── webapp/
│ ├── project.yaml # Project metadata
│ ├── board/
│ │ ├── item-001.md # Markdown + YAML frontmatter
│ │ └── item-002.md
│ └── learnings/ # Project-scoped learnings
│ └── learning-001.md
├── learnings/ # Cross-project learnings
│ └── learning-001.md
└── memory/
├── decisions.md # Key decisions + rationale
└── patterns.md # Discovered conventions
Architecture
src/agendum/
├── server.py # MCP server wiring (FastMCP)
├── tools.py # 14 MCP tools
├── models.py # Pydantic models (BoardItem, WorkPackage, SearchResult)
├── task_graph.py # Dependency resolution + topological levels
├── config.py # Shared configuration
├── env_context.py # Git diff/log auto-extraction
├── cli.py # CLI interface
├── enrichment/
│ ├── pipeline.py # ContextEnricher, budget allocation
│ └── sources.py # ProjectRules, Memory, Dependency, Learnings sources
└── store/
├── board_store.py # BoardItem CRUD
├── board_format.py # Markdown <-> BoardItem serialization
├── project_store.py # Project metadata
├── memory_store.py # Scoped memory storage
├── learnings_store.py # Global and project-scoped learnings
├── search_index.py # FTS5 + vector + entity graph + RRF
├── embedding.py # Lazy fastembed wrapper (optional)
└── locking.py # get_lock() + atomic_write()
Development
git clone https://github.com/sralli/agendum.git
cd agendum
uv sync
uv run pytest tests/ -v # all tests
uv run ruff check . # lint
uv run ruff format --check . # format check
License
MIT
Agendum MCP questions
How do I add Agendum MCP to Claude Code?
Run claude mcp add agendum -- uvx agendum in your terminal. Add --scope user to make it available in every project.
How do I add Agendum MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Agendum MCP provide?
It exposes 14 tools, including pm_init, pm_project, pm_status, pm_add, pm_board.
What problem does Agendum solve for AI agents?
It addresses the stateless nature of AI coding agents by providing persistent project state, bounded work packages, and cross-session continuity.
How does Agendum handle task dependencies?
It uses a dependency graph with topological ordering and cycle detection, allowing tasks to unblock automatically when their dependencies are completed.
Where is the project data stored?
All state is stored in human-readable Markdown and YAML files within a .agendum/ directory, making it git-native and diffable.
Can I use semantic search with Agendum?
Yes, by installing the optional vector extension, you can add semantic similarity search using fastembed and sqlite-vec.