A memory layer for fractional operators and independent consultants. Claude and ChatGPT do not retain what you decided last week; this does. $1 for 14 days.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · api.noheadcount.com
31tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://api.noheadcount.com/mcp
Skill page: https://www.mcpbundles.com/skills/noheadcount-mcp-a88609c8ee
Explore capabilities (31)
read 11
write 14
Showing 25 of 31
Showing 25 of 31 tools from the public preview. Connect the server to inspect the full live tool list.
Get3
List3
Save3
Query2
Update2
Other capabilities12
Get Subscription Info
read
get_subscription_info
Check your subscription status and usage stats.
Shows your current plan and, for expired/free accounts, how to subscribe.
Available to all users regardless of plan.
Get Subscription Info — Check your subscription status and usage stats.
Shows your current plan and, for expired/free accounts, how to subscribe.
Available to all users regardless of plan.
Create Project — Create a new client / engagement / project in the user's workspace.
Call this proactively when the user mentions starting work with a new
client ("kicking off with Acme", "new engagement with Hugo", "signed a
new client") — do not ask permission. Match spelling to what they said.
Args:
name: Client or project name as the user says it ("Breezy", "Acme Corp Q2")
description: Brief description of the engagement scope
contacts: Key contacts, comma-separated
List Projects — List your projects, filtered by status.
Args:
status: Filter by status. Options: active, paused, completed, archived, all. Default: active.
Get Project — Get full details for a specific project.
Args:
project_id: The project's ID number
Update Project — Update a project's state. Call proactively on phase/focus shifts.
Listen for state signals in the conversation and update without asking.
Trigger phrases (call without asking permission):
- "we're moving into build mode" / "this is now in discovery" → update phase
- "the priority for Breezy this week is X" → update current_focus
- "wrapping up that engagement" / "we're done with Acme" → status="completed"
- "pausing on that client for now" → status="paused"
- "kicke
Add Task — Add a task. Call proactively when the user narrates something they need to do.
Listen for commitment language and auto-capture without asking permission.
Trigger phrases (call without asking permission):
- "Sarah asked me to..." / "[name] wants..." / "I told them I'd..."
- "I need to..." / "I should..." / "reminder to..."
- "follow up on..." / "circle back to..." / "loop in [name]"
- Any due-date signal ("by Friday", "end of week", "before the call") tied to an action
List Tasks
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
What is the No Headcount — Your practice, remembered. MCP server?
A memory layer for fractional operators and independent consultants. Claude and ChatGPT do not retain what you decided last week; this does. $1 for 14 days.
How do I connect No Headcount — Your practice, remembered. to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate this server?
Request removal if you do not want No Headcount — Your practice, remembered. listed here, or claim the listing if you want to manage it on MCPBundles.
Operate No Headcount — Your practice, remembered.?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
— List your tasks with optional filters.
Shows open tasks by default. Filter by status, priority, or project.
Args:
status: Filter by status (open, in_progress, done, cancelled, all). Default: open tasks.
priority: Filter by priority (P1, P2, P3). Empty = all priorities.
project_id: Filter by project ID. 0 = all projects.
Update Task — Update an existing task.
Only pass the fields you want to change. Empty strings are ignored.
Args:
task_id: The task's ID number
task: Updated task description
priority: New priority (P1, P2, P3)
status: New status (open, in_progress, done, cancelled)
due_date: New due date (YYYY-MM-DD)
notes: Updated notes
Complete Task — Mark a task as done.
Shorthand for updating status to 'done'. Call this when a task is finished.
Args:
task_id: The task's ID number
Log Time — Log a time entry. Call proactively when the user mentions hours worked.
Listen for time signals and capture without asking.
Trigger phrases (call without asking permission):
- "spent 2 hours on..." / "just worked 90 min on..."
- "that call ran long, we went 45 min" → entry_type="meeting"
- "been heads-down on Breezy all morning" → estimate a reasonable block
- "just finished a session on..." / "wrapped up that call"
- At session wrap: if the user narrated work but h
Time Summary — Show a time tracking summary.
See how you spent your time, broken down by project and type.
Args:
period: Time period to summarize (week, month). Default: week.
project_id: Filter to a specific project. 0 = all projects.
Morning Briefing — Get your daily morning briefing.
THE daily driver. Assembles everything you need to start your day:
last session context, overdue and due-today tasks, open P1s, time
logged this week, and active project summary.
Call this when you say "what's on my plate?" or start your workday.
Record Decision — Capture a decision the user made. Call proactively when they narrate one.
Decisions are first-class memory. When a user says "we decided to...",
"going with X over Y," "scope change," "final answer," "locked in," etc.,
capture it without asking permission. Link to a project when possible
by matching the project name the user mentions.
Trigger phrases (call without asking permission):
- "we decided to..."
- "going with X over Y"
- "final answer" / "locked in" / "
Query Decisions — Query the decision log. Use for "what did we decide about..." questions.
Args:
project: Filter by project name.
category: Filter by category (see record_decision for valid values).
tag: Filter by a single tag.
status: "active" (default), "superseded", "reversed", or "all".
limit: Max results (default 20, hard max 100).
Supersede Decision — Mark an old decision as superseded by a new one. Use when the user says
"we're changing our minds about X" or "that's no longer what we're doing."
Creates a new decision, links the old one via superseded_by.
Args:
old_decision_id: The id of the decision being replaced (see query_decisions).
new_decision: The new decision text.
rationale: Why the change (important for audit trail).
category: Category for the new decision. Defaults to old decision's ca
Save Commitment — Record a commitment made to a client or stakeholder.
A commitment is a promise or obligation ("I'll send the report by Friday",
"we committed to delivering X"). Different from a decision - it's a pledge
to do something, not a choice between options.
Trigger phrases (call without asking permission):
- "I promised them..." / "I committed to..."
- "they're expecting..." / "I told them I'd..."
- "we're on the hook for..."
- "I said I'd get that to them by..."
-
Save Clarification — Log an item that needs clarification - something noted but not yet resolved.
Use for things the user said that could be a decision but aren't explicit
enough to commit ("I'm leaning toward Pylon", "we might go with X").
These surface in the clarification queue for follow-up.
Trigger phrases (call without asking permission):
- "I'm leaning toward..." / "probably going to..."
- "we might go with..." / "thinking about using..."
- "not sure yet, but..." / "still evaluat
Query Extracted Items — Generic filter across all extracted item kinds: decision, commitment, clarification.
Use when you need to see across all kinds at once, or when filtering by a
kind that query_decisions doesn't cover.
Args:
kind: Filter by kind: "decision", "commitment", "clarification", or "" for all.
project: Filter by project name.
category: Filter by category (applies mainly to decisions).
tag: Filter by a single tag.
status: "active" (default), "supersede
Get Project State — Get an oriented rollup for a project: phase, focus, last session, active
decisions, open task count, total hours.
Use when the user asks "where are we with X?" or "give me a rundown on Y."
Args:
project: Project name (case-insensitive substring match).
Search My Work — Full-text search across the user's accumulated workspace.
Searches ingested chunks first, then session notes, then extracted items.
Use when the user asks "what did I say about X" or "find that thing from Y."
Args:
query: Search text. Can be a phrase or keywords.
project: Optionally filter by project name.
document_type: Filter chunks by type (session/meeting/deliverable/research/client_context/note/email/decision/other).
limit: Max results (default
Save Session Context — Save the current session's summary. Call proactively when the user
signals they're wrapping up (or at end of a meaningful work block).
Unlike v2's save_context, this is a richer endpoint that also feeds the
server-side extraction pipeline (Phase 1.4): decisions and tasks mentioned
in the summary get mined automatically and written to their tables.
Trigger phrases (call without asking permission):
- "let's wrap up" / "that's enough for today" / "I'm done"
- "let's ca
List Pending Clarifications — Return the top pending clarifications for this user, ordered by priority.
Call this at natural review moments (bootup, session close, or when the
user asks to calibrate). Do not call mid-flow; defer clarification prompts
to wrap-up per §7.2.
Args:
limit: Max rows to return. Capped at 5 for adaptive session-close use.
min_priority: Drop rows below this priority (0.0-2.0 range).
project: If provided, restrict to clarifications whose subject items
Answer Clarification — Answer a pending clarification and propagate the result.
When the propagation would affect more than 5 items, returns a preview
with project breakdown + a `propagation_token`. To commit, re-call with
`confirm='yes'` AND pass back the token. If the affected set changes
between preview and confirm, the token will no longer match and the
tool will reject the confirm so you can review the updated preview.
Pass `scope='recent_7'` to narrow to items within the last 7 days;
Skip Clarification — Mark a clarification as intentionally not answered. Won't re-ask for 30 days.
Use when the user says this question is not worth answering, or that
the subject item should stay as-is. Does not update the subject item.
Defer Clarification — Defer a clarification to later. Lowers priority and pushes expiration out.
Use when the user isn't sure yet, or wants to answer later.
Showing the first 25 tools — full list and schemas: Directory API.
How many tools does No Headcount — Your practice, remembered. provide?
MCPBundles probed 31 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does No Headcount — Your practice, remembered. require?
No Headcount — Your practice, remembered. may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.