Agendum MCP server

by sralli·io.github.sralli/agendum·v0.3.4·6 stars

No reviews yet

AI agent memory: task tracking, scoped work packages, decisions, and cross-session continuity

B82/100grade B

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

B82/100

full report

Adoption

New

6 stars

Reviews

Write one

Nobody has reviewed Agendum yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agendum tools (14, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

pm_add
Add a new item to a project board. Supports type (dev/docs/ops/research/review/planning/personal/email), priority (critical/high/medium/low), tags, dependencies, acceptance criteria, key files, constraints, and notes. Use for ad-hoc tasks not from a plan file.
pm_block
Report a task as blocked with a reason. Updates the task status and logs the blocker. Use when a task cannot proceed due to external dependencies, missing information, or upstream blockers.
pm_board
View the project board with optional filters. Filter by status (pending/in_progress/blocked/done), tag, or type. Returns a markdown table of all matching items. Use to survey the full backlog or check status of specific categories.
pm_consolidate
Clean up memory corruption and near-duplicate learnings. Strips XML/tool-call fragments from memory scopes, finds near-duplicate learnings (same 50-char prefix) and marks extras as superseded, then rebuilds the search index. Call when pm_status reports corrupted entries or after large import operations.
pm_done
Report task completion. Records decisions, patterns, and learnings to project memory, logs files changed, and auto-unblocks dependent tasks. Pass decisions for architectural choices worth remembering, patterns for reusable conventions, and learnings for project-scoped insights. Set verified=True after running tests to mark as verified.
pm_ingest
Import tasks from a markdown plan file into the project board. Parses headings as task titles, extracts acceptance criteria, key files, and dependencies. Creates bounded board items with dependency tracking. Call after creating a project to populate the board from an existing plan.
pm_init
Initialize the agendum board directory. Call once per repository or home directory to set up project tracking. Creates .agendum/ with projects, learnings, and memory subdirectories. Returns confirmation. Next step: create a project with pm_project.
pm_learn
Record a learning. Pass 'project' for project-scoped learning, omit for global cross-project learning. Tagged insights enrich future work packages. Use for patterns, gotchas, or conventions. Examples: 'Clerk proxy.ts must be at app/ level' tagged 'auth,clerk,nextjs'. Provide comma-separated key entities, concepts, technologies, and file paths mentioned in the content as `topics` to enable graph-ba
pm_memory
Read, write, append, or search project memory. Scopes: 'decisions' (architectural choices), 'patterns' (conventions and gotchas), 'project' (general project knowledge), 'learnings' (cross-project insights). Use to persist or retrieve knowledge across sessions.
pm_next
Get the next scoped work package. Returns a bounded context packet with task details, acceptance criteria, relevant memory, dependency context, and project rules. Automatically marks the task as in-progress. Call at the start of a work session or after completing a task with pm_done.
pm_projectwrite action
Create, list, or get projects. Actions: 'create' (requires name), 'list' (shows all projects), 'get' (shows project details with spec/plan excerpts). Call after pm_init to set up a project, or anytime to inspect existing projects.
pm_search
Search all agendum knowledge — memory, learnings, completed board items. Uses ranked full-text search with porter stemming (auth matches authentication, etc). Filter by source_type ('memory', 'learning', 'board_item') or project slug.
pm_status
Get a status overview for one or all projects. Shows item counts by status, recent progress, recent decisions, and suggested next task. Call at the start of a session to understand current state, or after completing work to see what's next.
pm_supersede
Soft-invalidate a learning by marking it superseded. The entry is excluded from all future searches. Pass entry_id (e.g. 'learning-003'), optional project slug for project-scoped learnings, and optional reason describing what superseded it.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings

Code scan23 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 167 days ago8/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Agendum compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 82/100; higher than 58% of 1,299 Productivity servers
Tools: 14; the typical Productivity server has 7
Tools that change things: 7%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 6; more than 72% of 854 Productivity servers

What its tools let an agent do: 13 read · 1 change

Install Agendum in Claude Code, Cursor or VS Code

claude mcp add agendum -- uvx agendum

Add to Cursor

What the publisher says

From the Agendum repository's README, as published. We do not edit it. Read it on GitHub

agendum

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.

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 pmdone records decisions and patterns that enrich future pmnext 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

Planning & Backlog

Execution Loop

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agendum: common questions

Is Agendum MCP server safe?: Mostly: it is graded B (82/100). Read the Agendum safety report
How do I install Agendum?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agendum need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agendum maintained?: The last commit was 205 days ago (2026-04-13). The latest release is v0.3.4.
What can I use instead of Agendum?: Servers from other publishers that do the same job: loci MCP server, Agent-Native Dispatch MCP server and Exomem MCP server.
How does Agendum compare with other Productivity MCP servers?: safety score 82/100 (higher than 58% of 1,299 Productivity servers); tools 14 (the typical Productivity server has 7); tools that change things 7% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agendum

Same job from other publishers: the closest match first, then the best rated.

loci
Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
not reviewed
Established
A
Agent-Native Dispatch
Central Slack/Telegram router with jobs, memory, approvals, and A2A delegation
More from BuilderIO →
not reviewed
Established
A
Exomem
Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.
not reviewed
Established
A
Mdma
MCP server for MDMA — exposes spec, prompts, docs, and package metadata to AI assistants.
not reviewed
Growing
A
INSSIST
Drive your own logged-in Instagram session via the INSSIST extension: read, publish, DMs, analytics.
not reviewed
Growing
A