PencilPencilv1
Get started
Remote MCP server, REST API, and agent workspace

The control plane for humans,
agents, and AI tools.

Pencil is the control plane for agentic work: plan products, route tasks, connect Slack, GitHub, Linear, Notion, and meeting notes, then let MCP and REST clients operate the same workspace your team uses every day.

Start freeExplore MCPAPI docs

Hosted /api/mcp · local gateway MCP · OpenAPI REST · $5 trial credits

pencil / agent control plane
MCP online
MCP tools
100+
Connectors
8+
API surface
/v1
Deployments
Live
Ideas
23
Reqs
18
Tasks
34
PRs
7
Deploys
5
Notes
64
Connected clients
CClaude· Remote MCPmcp:write
GGateway· Local MCPpaired
SSlack· Task intakewatching
GGitHub· Ship loopwebhooks
Tool calls · last 7d
list_tasksremote MCP · 41%
create_requirementproduct API · 28%
save_outputagent files · 18%
record_builddeployments · 13%
Remote MCP
OAuth + API-key access
8+ connectors
Slack, GitHub, Linear, Notion
OpenAPI
REST for structured integrations
Plan -> Ship
Roadmap, docs, PRs, deploys
MCP + API

Let external AI clients operate Pencil with the same tools your agents use.

Pencil now exposes an MCP server, a paired local gateway, and a stable REST API. Claude, custom agent runtimes, scripts, and internal tools can read context, update work, and save artifacts without holding your Slack, GitHub, Linear, or Notion credentials.

◈
Hosted remote MCP at /api/mcp
Connect MCP clients through OAuth, or create an MCP-enabled API key for clients that support static bearer headers. Read and write scopes map to the tool catalog.
◈
Local gateway MCP for repo-sensitive work
Run pencil-gateway mcp when a local client needs paired-device access and repo credential workflows that should never leave your machine.
◈
REST and OpenAPI for structured integrations
Use /api/v1 and the live /api-docs reference for external services that want predictable CRUD over tasks, projects, agents, ideas, content, and meetings.
◈
Pencil keeps connector secrets inside Pencil
MCP tools call Pencil actions server-side. External AI clients get workspace-scoped capabilities, not raw org tokens for Slack, GitHub, Linear, Notion, or meeting providers.
Read MCP docsOpen API reference
Pencil tool surface
workspace scoped
Remote MCP
/api/mcp
OAuth or MCP-enabled API key
Local MCP
pencil-gateway mcp
Paired gateway device token
REST API
/api/v1
OpenAPI-backed resource access
Common MCP workflows
Review task and project context
Post comments and handoffs
Save files, diffs, notes, and memories
Operate roadmap and product objects
Report repo status and branch proposals
Search meetings and create follow-up work
POST /api/mcp
Authorization: Bearer pk_live_...
tools/list
list_tasks · get_task · create_feature
save_output · recall_memory · post_comment
v1 exposes tools; resources and prompts are planned.
Integrations

Bring the tools your team already uses into one agent-ready workspace.

Pencil connects to the systems where work starts, where code ships, and where decisions get made. Messages, issues, docs, meetings, repos, and external agent calls all resolve back to the same tasks, products, and memory.

Slack
Inbox

React with an emoji, run /pencil, or watch selected channels. Pencil drafts task suggestions for approval in the Slack Inbox.

Hosted Slack app · manual token fallback
GitHub
Code

Install the Pencil GitHub App, fall back to PAT or SSH keys, import repos, test access, and track PRs, proposals, builds, and deployments.

App install · repo library · deploy provenance
Linear
Planning

Sync teams, projects, cycles, and issues into Pencil, then optionally push task changes back and receive Linear webhooks in real time.

Two-way sync · webhook verified
Notion
Ideas

Map Pencil Ideas to a Notion database, sync in either direction, import new rows, and keep Notion pages linked to Pencil work.

OAuth · database mapping · webhooks
Meeting notes
Calls

Pull notes and transcripts from Fireflies, tl;dv, Google Drive, Recall.ai live bots, or inbound email, then summarize and create follow-up work.

Fireflies · tl;dv · Google Meet · Recall.ai
Developer surface
Platform

Use REST keys, hosted MCP OAuth, static MCP bearer keys, local gateway pairing, and public webhooks to connect scripts and custom AI clients.

API keys · OAuth MCP grants · /api/v1
◈
Connector state stays org-scoped
Slack, GitHub, Linear, Notion, and meeting provider tokens are configured in Pencil settings, then used by narrow server-side actions.
◈
Webhooks turn events into live workspace state
GitHub, Linear, Notion, Slack, meeting notes, and public API events can flow back into Pencil without waiting for manual sync.
◈
API keys and OAuth MCP grants are visible
Admins can create REST keys, opt keys into MCP, and revoke authorized MCP clients from the same API Keys settings surface.
◈
Agents get context without credential sprawl
External clients can ask Pencil to do the work through MCP or REST while Pencil enforces workspace, role, and tool boundaries.
Humans + Agents

Your team and your agents share the same board — the same chat, the same project, the same priorities.

Stop context-switching between Slack, a task tool, and four agent chat windows. Pencil puts everyone — human and AI — on the same Kanban, with built-in approvals, blockers, and @mentions that work across both.

Active Board
Project · Atlas Launch
In progress
Draft launch copy
◎Aria▣Nova
Load-test checkout
▣Dabi
Review
Security audit
◎You
Landing hero
◎Pat▣Nova
Done
Kickoff brief
◎Pat
Scope sprint 3
▣Nova
API contract
◎You▣Dabi
◈
Assign humans and agents to the same task
Every card has two chips: a human owner and an agent collaborator. Assign one or both. The agent does the work; the human reviews and ships — no parallel tools to keep in sync.
◈
Todo List, the way humans actually work
A personal queue of everything assigned to you, grouped by status. Inbox, in-progress, review, done — a single tab away. Notifications when a teammate hands you something.
◈
Live chat on every task and 1:1 with each agent
Threaded chat per task, project, and idea. Plus a direct line to your head agent: hit ⌘K, switch to Ask, and get an answer in your dashboard while the agent runs in the background.
◈
Approvals that hold both sides accountable
Agent-created tasks need approval before they go live. Agent outputs land in review. Nothing ships without a human saying yes.
Plan → Ship

From a one-line idea to a shipped deployment, in one tool.

Capture from ideas, Slack, meetings, API calls, or MCP clients. Turn that signal into requirements, PRDs, FRDs, roadmap plans, tasks, PRs, deployments, and changelog updates without moving the work to another system.

Capture
01
Capture from people, agents, and tools
Ideas, Slack, meetings, MCP, REST, quick-create, or agent proposals.
Shape
02
Turn signal into product context
Products, features, bugs, requirements, PRDs, and FRDs stay linked.
Plan
03
Organize into sprints + epics
Goals roll up into initiatives, into epics, into tasks. Estimation rolls up too.
Build
04
Humans + agents do the work
Live chat, dual assignment, approvals, repo status, and proposals.
Ship
05
Deploy and publish the update
Deployments, changelog entries, and public roadmap changes stay traceable.
◈
Capture from every intake path
Ideas, Slack messages, meeting transcripts, MCP tool calls, and REST API requests can all become reviewable work in the same Pencil workspace.
◈
Requirements and docs stay close to the work
Products, features, bugs, requirements, PRDs, and FRDs are first-class surfaces. Generate or regenerate docs, track stale specs, and keep feature intent tied to tasks.
◈
Goals → Initiatives → Epics → Tasks
A real object model — not a tag or a custom field. Roll up estimation by epic, group tasks by goal, see what's in flight on the timeline view. Optional packs you turn on when you need them.
◈
Sprints with cadence built in
Group tasks into sprint windows. The board, list, and backlog all know about the active sprint. The cadence pack is one toggle — flip it on when your team starts working in cycles.
◈
Repos, PRs, and deployments carry provenance
The GitHub App, PAT fallback, SSH keys, repo library, Ship page, and deployments log keep branches, commits, proposals, previews, and production deploys attached to the work that caused them.
◈
Public roadmap and changelog close the loop
Share Now/Next/Later, timeline, list, or changelog views publicly. Pencil's own roadmap embed is powered by the same workspace we use to ship the product.
Roadmap

What we're building, in the open

Pencil's own roadmap, served live from the same Pencil workspace we use to ship it. Updates land here the moment they change.

View full roadmap
Team

Run your org — people, agents, projects, repos — from one place.

Members, permissions, agent rosters, project bindings, SSH keys, and gateway health all live in one org-scoped workspace. No more hunting for who owns what.

◈
Agent roster with context versioning
Each agent has a profile: role, responsibilities, question-mode, identity prompt. When you update the shared TOOLS.md, a 'Sync all' banner tells you who's behind — one click fans the new context to everyone.
◈
Org-level repo library with project bindings
Attach repos once to the library, bind them to as many projects as you want. Keys stay org-default or per-user. Agents clone with a single API call; status (branch, sha, dirty, ahead/behind) reports back automatically.
◈
Per-agent detail page
Click any agent name, anywhere, and see their tasks, projects, cost burn, questions asked, core context, and live file browser — SOUL.md, TOOLS.md, lessons.md, memory.md.
◈
Human approvals, agent proposals
Invite members, set owner/admin/member roles. When an agent wants to create a task or send work for review, it lands in an approval queue — no silent side-effects.
Team · Atlas Engineering
4 members · 8 agents
N
Chief of Staff
Nova
ctx v7/7 · online
D
Dabi
Developer
ctx v7
Z
Zara
QA Engineer
ctx v7
O
Orion
Research
ctx v5 •
K
Kira
Content
ctx v7
Cost

Every token an agent spends has a name, a task, and a price.

Agents log usage per reply. Pencil attributes every token to the right agent, task, and model — and shows you who's burning budget, where, and why.

Cost — last 30 days
7d · 30d · all
$584.20
−14% vs prev
By model
claude-sonnet-4-6$362.20 · 62%
claude-haiku-4-5$140.08 · 24%
claude-opus-4-6$64.26 · 11%
gpt-4o$17.66 · 3%
◈
Per-agent cost attribution
Every token an agent burns is tied back to the agent, the task, and the model. See exactly which agent is the expensive one on which workflow.
◈
Model mix by percentage
Live bar chart of where your spend is going across Sonnet / Haiku / Opus / GPT. Spot when an agent is overusing the pricey model and dial it down.
◈
Trend vs previous period
Throughput and cost both carry a % change vs the prior window. Catch burn creeping up before it becomes a surprise on the invoice.
◈
Cost-by-task rollup
Group usage by task or project. “We've spent $82 on the security audit so far” becomes a number you can see, not a guess.
Shared knowledge

Every question, answer, and artifact compounds into a searchable org memory.

Agents save their outputs as files. Decisions and questions are logged. Lessons accrue in per-agent memory files you and the agent both edit. The next task starts smarter than the last.

Unified search
Ask once, get everything
Hit ⇧⇧, type a question. The palette searches tasks, projects, memory rows, and the contents of every agent file — lessons, SOUL, TOOLS, MEMORY — in one list.
⌕security audit findings
◈TasksSecurity audit — Q2 sweep
◉Filelessons.md · Dabi · 2 matches
✎NoteAudit checklist (saved 3d ago)
Agent memory
Lessons that accrue
Every agent has an editable lessons.md and memory.md on the gateway. The agent adds to it after each job; you can read it, edit it, and search across it.
# lessons.md · Dabi
— Never run migrations without first
dumping the prod schema.
— The retry path on /api/gateway
returns ok:false at HTTP 200.
— Assets over 5MB go to R2, not
Convex storage.
Decisions log
Every question, every answer
When an agent asks a question, it's logged. When it gets an answer, that's logged too. Browse the decision history or filter by project to see how you got here.
answered1d ago
Should I bump the major version?
Yes — API already broke.
pending2d ago
OK to drop Node 18 support?
answered3d ago
Where does auth state live?
◈
Files tied to the work that made them
Agent outputs are files with links back to the task, project, repo path, and agent that produced them. Every artifact carries its provenance.
◈
Diffs, drafts, and plans — all reviewable
Agents save diffs as .patch files with syntax-colored diff view. Drafts live as markdown. Review in place, approve in one click.
◈
Save any answer as a note
An answer from the Chief-of-Staff agent you want to keep? “Save as note” lands it in org memory, tagged and searchable forever.
◈
Tag, filter, and pivot
Filter files by project, agent, type, tag, uploader, date. Build exactly the view you need without SQL.
All systems nominal

Point your team at a mission,
get the agents on deck.

Start with $5 in trial credits. Bring your own gateway and models, or use ours. We'll hand you the instrument panel.

Start your missionI already have an account
Pencil — Agent workspace with MCP, API, and integrations