markplane

Markplane is a local, markdown-first project management tool for organizing epics, tasks, plans, and notes inside a repository (e.g., .markplane/). It generates a token-efficient .context/ directory for AI assistants and includes a built-in MCP server (JSON-RPC over stdio) plus a local web UI to manage and visualize project state.

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ DevTools project-management task-management mcp cli rust markdown ai-context web-ui local-first
⚙ Agent Friendliness
58
/ 100
Can an agent use this?
🔒 Security
26
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
70
Error Messages
0
Auth Simplicity
90
Rate Limits
0

🔒 Security

TLS Enforcement
20
Auth Strength
20
Scope Granularity
0
Dep. Hygiene
30
Secret Handling
60

Local-first tool with no hosted service described; this reduces network attack surface but increases reliance on local environment safety. TLS is only relevant for the local web server; no documentation provided about TLS configuration. No auth/RBAC model is described for MCP/web UI (implies trust in local user/process). Dependency hygiene and secret handling practices are not verifiable from provided README alone.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
35
Error Recovery
35
AF Security Reliability

Best When

You want project management data to live in the same repo as the code (git-backed), and you want AI assistants to reliably read/update that state via an MCP integration and/or local UI/CLI.

Avoid When

You cannot run local binaries/web UI/MCP locally (e.g., locked-down environments), or you need fine-grained, server-enforced access controls and external compliance features that are not provided by a local file-based model.

Use Cases

  • Keep repo-scoped project plans/backlogs versioned with code in git
  • Provide an AI-friendly context layer (.context/ summaries + INDEX.md routing) for coding assistants
  • Manage tasks/epics/plans with CLI and sync updates to a local web dashboard
  • Use MCP-enabled AI assistants to query/update tasks and dependencies via natural language
  • Track dependencies/blocks between work items and surface blocked work
  • Maintain structured decision logs via markdown notes with status workflows

Not For

  • Teams that require a hosted, multi-tenant SaaS workflow with centralized accounts
  • Organizations that need server-side RBAC/audit logs across many projects
  • Use cases that require an external database as the source of truth (Markplane is file-based)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: None for local CLI/Web UI and MCP transport is stdio-based (per README)
OAuth: No Scopes: No

No hosted API/auth model is described. MCP integration is configured locally via editor config pointing to the `markplane mcp` command.

Pricing

Free tier: No
Requires CC: No

Licensing is Apache-2.0 per repo metadata; no usage-based pricing described in provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • MCP operates over stdio; some agent/editor setups may require correct per-user vs project-wide configuration (e.g., .mcp.json).
  • Agent may need to use INDEX.md routing/context-loading patterns described in docs to stay within token budgets.
  • File-based state means concurrent edits (manual + agent + UI) could create conflicts; conflict behavior is not described in provided content.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for markplane.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered