makermap
REST + MCP - ONE BACKEND

The command layer for people who build with agents.

Every single capability is also an MCP tool. Products, plans, decisions and time in one operational picture - and your agents work the same surface you do, while you stay the one who decides.

Free forever for one maker - 3 products, no card.

YOU, IN THE APPAwaiting you

Ship v0.4 behind the launch gate, or hold for the audit?

Tidepool2 alternatives - opened 2d ago
release-agent - advisoryconfidence 0.72

Gate LAUNCH-1 has 4 of 5 conditions met. The open one is the security review, unassigned for 6 days. Recommend holding - but this is your call.

only a person can end this
YOUR AGENT, OVER MCPpat - decisions:write
$ get_product_context product="tidepool"
-> 9 sections, 1 decision awaiting a human
$ post_advisory decision=dec_8fa2 confidence=0.72
-> advisory recorded. The decision stays open.
$ decide_decision decision=dec_8fa2
! refused: decide_decision is human authority

288 tools, the same services the panel on the left is built from. An agent can read everything and propose anything - and is refused exactly where a person has to sign.

One backend. Two front doors. Nothing an agent does is invisible to you, and nothing you do is hidden from it.

288tools over MCP, every one of them a real capability
9sections of product context in a single call
0numbers on a screen without an explanation
1act ends a decision, and a person performs it
WHAT IT ACTUALLY DOES

Everything you run, an agent can run too

From the first idea to the launch gate - and the same surface an agent works from.

Command Center

One home that tells you what needs a decision, which products went quiet, and what changed - every row explaining itself in words and leading straight to where you act.

Plan versus actual

Time is its own layer. Initiatives, milestones, releases and dated tasks share one timeline, with the plan drawn against the actual that really happened.

Initiatives

The container between a product and its tasks: the large change you are betting will move it, tying an intended outcome to the epics and the gate that carry it.

Milestones & releases

Ship on real checkpoints. A release publishes only when its launch gate passes - never a flag someone flips - and the moment it shipped is recorded as a fact.

Capture, then formalize

Drop a thought onto the timeline in five seconds; turn that same block into a task, epic, milestone or initiative later, its origin preserved.

Decisions & design reviews

A human-in-the-loop queue where agents advise and a person decides. A visual review carries typed mockups, anchored comments and advisory votes.

Knowledge & logs

Long-form memory that survives a session hand-off, plus append-only named logs read from the tail - ask for the last three entries, not the whole file.

Gates that explain themselves

Real checkpoints with manual, automated and AI-assessed conditions. A refused transition names the gate, its unmet conditions and the exact next call.

Production readiness

Six checklists say what "done" means for deploy, auth, payments, security, tests and the store. makermap knows what must be checked, remembers who signed off and when, and says when that went stale. It never looked at your systems itself, and the record says so on every line.

Agent-grade over MCP

Scoped tokens, one-call product context, cursor pagination, permission-aware discovery, and the project docs themselves searchable section by section.

THE TEMPORAL LAYER

Time is a layer, not a column

Nothing in makermap carries its own private dates. Initiatives, milestones, releases and tasks all hang off one canonical timeline, which is why the plan and the actual can be drawn on the same row - and why an overdue item can turn critical and say so, instead of just sitting there.

  • One span per thing that happens, so a date is never duplicated and never drifts
  • Slip is computed against the plan and explained in words, not colour alone
  • Move a milestone and everything that hung off it moves with it
Tidepool - Q3planactual
JulAugSepOct
Multi-tenant rolloutInitiative
Beta milestoneMilestone
v0.4 releaseRelease
Security reviewTask
Security review is 12 days past its planned end and blocks gate LAUNCH-1.
POST/gates/LAUNCH-1/transition409
{
"code":"GATE_NOT_PASSED"
"message":"Gate LAUNCH-1 cannot pass: 1 of 5 conditions is unmet."
"hint":"Complete 'Security review' (tsk_41c), then retry."
}
GATE LAUNCH-1 - CONDITIONS
Acceptance tests greenautomated
Runbook publishedmanual
Rollback verifiedmanual
Cost forecast reviewedai-assessed
Security review completemanual
GOVERNANCE

No refusal is ever a bare no

An agent that is told "forbidden" learns nothing and retries forever. So every refusal in makermap names what stopped it, why, and the exact next call that would succeed - the same answer over REST and over MCP, because both are the same service.

  • Gates carry manual, automated and AI-assessed conditions - and a release publishes only when its gate passes
  • Scoped tokens: an agent gets exactly the verbs you granted, and discovery only shows those
  • Every consequential change lands in an append-only log that says who, when and why
PRICING

You pay for people. Agents are never a seat.

Add as many agents as you like - they cost nothing to connect. A shared pool of credits covers the one thing that has a real machine cost.

Free

For one maker, forever

$0forever, no card
Start free
  • 1 member
  • 1 workspace
  • 3 products
  • The full MCP surface
  • Decisions, gates, timeline, knowledge
  • Intelligence Layer: forecasts, lessons, scenarios
  • Audit export
  • Telemetry retention & redaction policy
  • SSO
  • Priority support

Pro

MOST CHOSEN

For a maker with a portfolio

$18per member / month
Start 14-day trial
  • Unlimited members - you buy seats
  • Unlimited workspaces
  • Unlimited products
  • Everything in Free
  • 1,000 agent credits included
  • Intelligence Layer: forecasts, lessons, scenarios
  • Audit export
  • Telemetry retention & redaction policy
  • SSO
  • Priority support

Team

For a team that ships together

$39per member / month
Talk to us
  • Unlimited members - you buy seats
  • Unlimited workspaces
  • Unlimited products
  • Everything in Pro
  • 5,000 agent credits included
  • Intelligence Layer: forecasts, lessons, scenarios
  • Audit export
  • Telemetry retention & redaction policy
  • SSO
  • Priority support

Credits bill compute, and only compute

Semantic search runs an embedding model, so it costs 1 credit. Saving a document, reading context, moving a card, posting an advisory, appending to a log - free, and always will be. Your balance is a running sum you can read at any time, with every charge naming what it paid for.

Put your portfolio and your agents on the same map

Sign up, mint a scoped token, paste one block of config. Your agent has the whole product in front of it.

One field, one email when a place opens. No newsletter, and nothing else is asked.

~/.claude/mcp.json
{ "mcpServers": { "makermap": { "url": "https://api.makermap.dev/api/mcp", "headers": { "Authorization": "Bearer mm_pat_..." } } }}

Works with any MCP client. The token decides what the agent may touch - discovery only lists the tools that token can call.