PutRoots
SF move agent: rentals with sources, no-SSN banking routes, and your move plan and drafts.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"putroots": {
"url": "https://www.putroots.com/mcp"
}
}
}Remote endpoints
https://www.putroots.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (11)
🟢search_listings(max_price, min_price, beds, hood, limit)
Search PutRoots' San Francisco rental index. Every row carries its source, the date we last saw it, and whether the landlord stated any requirements at all. Use this when someone asks what's available in SF at a price / bedroom count / neighborhood. Without a signed-in PutRoots account this searches the free sample only (3 listings per bedroom tier) and says so, with the true total.
Input Schema
{
"type": "object",
"properties": {
"max_price": {
"type": "number",
"description": "Max monthly rent in USD. Listings with no stated price are excluded when you set this — we don't let unpriced posts through a price filter."
},
"min_price": {
"type": "number",
"description": "Min monthly rent in USD."
},
"beds": {
"type": "string",
"enum": [
"room",
"studio",
"1",
"2",
"3+"
],
"description": "Bedroom tier. \"room\" means a room in a shared place."
},
"hood": {
"type": "string",
"description": "Neighborhood name, matched loosely (e.g. \"Mission\", \"Sunset\")."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "How many to return (default 10, max 25). Newest first."
}
},
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"gated": {
"type": "boolean",
"description": "true = free sample only (anonymous or partner key); total still tells the true index size."
},
"total": {
"type": "integer"
},
"searched": {
"type": "integer"
},
"matched": {
"type": "integer"
},
"not_checked_vs_budget": {
"type": "integer"
},
"listings_with_no_stated_requirements": {
"type": "integer"
},
"listings": {
"type": "array",
"items": {
"type": "object",
"properties": {
"url": {
"type": "string"
},
"title": {
"type": [
"string",
"null"
]
},
"price": {
"type": [
"number",
"null"
]
},
"beds": {
"type": [
"string",
"null"
]
},
"hood": {
"type": [
"string",
"null"
]
},
"source": {
"type": [
"string",
"null"
]
},
"posted": {
"type": [
"string",
"null"
]
},
"last_seen": {
"type": [
"string",
"null"
]
},
"requirements_stated": {
"type": "boolean"
},
"not_checked_vs_budget": {
"type": "boolean"
}
},
"required": [
"url",
"price",
"source",
"requirements_stated"
]
}
}
},
"required": [
"gated",
"total",
"searched",
"matched",
"listings"
]
}🟢listing_requirements(listing_url)
For one listing URL from search_listings: what the landlord requires, what the renter filled in, and the gap on each line — income, credit, SSN, deposit, pets, co-signer, documents. Each line carries the landlord's own sentence it was read from, plus where the rule came from and when we fetched it. Requires the renter's own PutRoots account (the comparison is against qualifications they filled in). It returns no overall verdict, by design.
Input Schema
{
"type": "object",
"properties": {
"listing_url": {
"type": "string",
"description": "The listing's url, exactly as returned by search_listings."
}
},
"required": [
"listing_url"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"listing": {
"type": "string"
},
"price": {
"type": [
"number",
"null"
]
},
"source": {
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"landlord_rules",
"listing_text"
]
},
"name": {
"type": [
"string",
"null"
]
},
"from": {
"type": "string"
},
"fetched_at": {
"type": [
"number",
"string",
"null"
],
"description": "Epoch ms for landlord rules; ISO date for listing text."
},
"fetched_from": {
"type": [
"string",
"null"
]
}
},
"required": [
"kind",
"from",
"fetched_at"
]
},
"triage_tier": {
"type": [
"string",
"null"
]
},
"summary": {
"anyOf": [
{
"type": "object",
"properties": {
"gaps": {
"type": "integer"
},
"askLandlord": {
"type": "integer"
},
"askYou": {
"type": "integer"
},
"met": {
"type": "integer"
},
"info": {
"type": "integer"
}
}
},
{
"type": "null"
}
]
},
"items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"label": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"meets",
"info",
"gap",
"unknown_user",
"unknown_landlord"
]
},
"required": {
"type": [
"string",
"null"
],
"description": "What the landlord wrote (null = not stated)."
},
"yours": {
"type": [
"string",
"null"
],
"description": "What the renter filled in (null = not filled in)."
},
"detail": {
"type": "string"
},
"blocking": {
"type": "boolean"
},
"src": {
"type": [
"string",
"null"
],
"description": "The landlord's own sentence this line was read from."
}
},
"required": [
"key",
"label",
"status",
"required",
"yours",
"detail"
]
}
}
},
"required": [
"listing",
"price",
"source",
"items"
]
}🟢newcomer_options(topic)
The doors a newcomer has to walk through besides the apartment: opening a bank account, a credit card, a phone plan, or getting an SSN — specifically the routes that work without an SSN or US credit history. Returns real branches and stores (address, hours, phone) plus the no-branch options, each with its source and the date it was checked, and our firsthand account where we did it ourselves.
Input Schema
{
"type": "object",
"properties": {
"topic": {
"type": "string",
"enum": [
"bank",
"card",
"sim",
"ssn"
],
"description": "bank = checking account, card = credit card, sim = phone plan, ssn = the SSN itself."
}
},
"required": [
"topic"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"topic": {
"type": "string"
},
"places_total": {
"type": "integer"
},
"places": {
"type": "array",
"items": {
"type": "object",
"description": "A branch / store: name, addr, tel, hours, the no-SSN line with its source."
}
},
"options": {
"type": "array",
"items": {
"type": "object",
"description": "A no-branch option: name, stance (official page) and firsthand stance, facts, url, source."
}
},
"prefNote": {
"type": [
"string",
"null"
]
},
"prefScope": {
"type": [
"string",
"null"
]
}
},
"required": [
"topic",
"places",
"places_total",
"options"
]
}🟢start_move(trigger, stage, d0, to, profile_seed)
When someone has just signed a lease, accepted an offer, or otherwise has a move coming: returns a PutRoots link that pre-fills their move date and new address and attributes them to you. Nothing is created on their behalf — they sign up themselves by opening the link. Use the returned id with GET /v1/handoffs/{id} to see which stage of the move they are in.
Input Schema
{
"type": "object",
"properties": {
"trigger": {
"type": "string",
"maxLength": 60,
"description": "What set the move off: lease_signed, offer_accepted, relocation_approved, or your own short label."
},
"stage": {
"type": "string",
"enum": [
"pre_arrival",
"housing",
"move_planning",
"move_logistics",
"activate",
"settle",
"stabilize"
],
"description": "Which stage of the journey they are in right now, if you know it."
},
"d0": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Move-in day, YYYY-MM-DD."
},
"to": {
"type": "string",
"maxLength": 200,
"description": "The new address, as one line."
},
"profile_seed": {
"type": "object",
"description": "Reserved. Accepted but not applied yet — the person fills their own profile after signing up."
}
},
"required": [
"trigger"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"url": {
"type": "string"
},
"partner": {
"type": "string"
},
"trigger": {
"type": "string"
},
"stage": {
"type": [
"string",
"null"
]
},
"d0": {
"type": [
"string",
"null"
]
},
"to": {
"type": [
"string",
"null"
]
},
"dry_run": {
"type": "boolean",
"description": "true when called with a pr_test_ key."
}
},
"required": [
"id",
"url",
"partner",
"trigger",
"dry_run"
]
}🟢move_plan
The whole move at a glance for the signed-in person: days to move day, how many tasks there are, how many are settled, how many can be done right now, how many are blocked and how many are overdue, plus the critical path. Two rulers share that answer and they are not interchangeable: total and done count every task in the move, while actionable, blocked and overdue count only tasks that have been unlocked so far. Blocked therefore mixes two things — tasks missing an answer from the person, and tasks whose prerequisites aren't finished so they haven't been generated yet. Report the numbers as given; don't subtract one from another.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"ok": {
"type": "boolean"
},
"d0": {
"type": "string"
},
"days_to_d0": {
"type": "integer"
},
"total": {
"type": "integer",
"description": "Every task in this move (full ruler)."
},
"done": {
"type": "integer",
"description": "Settled: done, sent, called, replied or marked not applicable (full ruler)."
},
"actionable": {
"type": "integer",
"description": "Unlocked and not waiting on an answer (unlocked ruler)."
},
"blocked": {
"type": "integer",
"description": "total - done - actionable: tasks missing an answer AND tasks not yet unlocked, together."
},
"overdue": {
"type": "integer",
"description": "Past due, not in flight, not blocked (unlocked ruler)."
},
"critical_path": {
"type": "object",
"properties": {
"ids": {
"type": "array",
"items": {
"type": "string"
}
},
"remaining": {
"type": "integer"
},
"first": {
"type": [
"string",
"null"
]
},
"blocks": {
"type": "integer"
}
}
},
"health": {
"type": "object",
"properties": {
"ok": {
"type": "boolean"
},
"line": {
"type": "string"
}
}
}
},
"required": [
"ok",
"d0",
"days_to_d0",
"total",
"done",
"actionable",
"blocked",
"overdue",
"critical_path",
"health"
]
}🟢move_tasks
What the signed-in person should do next on their move: one task to press, a few short lines after it, and a count of everything folded away. This is deliberately one screen, not the task list — picking which one matters is our job, not the caller's, and a task whose prerequisites aren't done doesn't appear at all (its prerequisite does). Use move_plan for totals. This is also the only place a task is marked in flight (we have evidence they already started it); move_task does not carry that flag.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"hero": {
"anyOf": [
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"state": {
"type": "string",
"description": "todo / blocked / drafted / approved / sent / called / replied / done / skipped."
},
"kind": {
"type": "string",
"description": "How it gets done: email, call, walk (fill a form on someone's site), research (find candidates / book / fill an application), or user (only the person can)."
},
"actor": {
"type": "string",
"description": "agent = we can do it for them; user = only they can."
},
"due": {
"type": "integer"
},
"dlabel": {
"type": "string"
},
"due_day": {
"type": "string"
},
"in_flight": {
"type": "boolean",
"description": "Evidence says they already started it, so it is not overdue and never the next thing to press."
},
"overdue_days": {
"type": "integer"
},
"unlocks": {
"type": "integer",
"description": "How many tasks that don't exist yet would appear once this one is finished."
},
"missing": {
"type": "array",
"items": {
"type": "string"
},
"description": "Field names this task is waiting on — pass one to move_task_answer."
}
},
"required": [
"id",
"title",
"state",
"kind",
"actor",
"due",
"dlabel",
"due_day",
"unlocks"
]
},
{
"type": "null"
}
],
"description": "The single next thing, or null with blockedReason set."
},
"rows": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"state": {
"type": "string",
"description": "todo / blocked / drafted / approved / sent / called / replied / done / skipped."
},
"kind": {
"type": "string",
"description": "How it gets done: email, call, walk (fill a form on someone's site), research (find candidates / book / fill an application), or user (only the person can)."
},
"actor": {
"type": "string",
"description": "agent = we can do it for them; user = only they can."
},
"due": {
"type": "integer"
},
"dlabel": {
"type": "string"
},
"due_day": {
"type": "string"
},
"in_flight": {
"type": "boolean",
"description": "Evidence says they already started it, so it is not overdue and never the next thing to press."
},
"overdue_days": {
"type": "integer"
},
"unlocks": {
"type": "integer",
"description": "How many tasks that don't exist yet would appear once this one is finished."
},
"missing": {
"type": "array",
"items": {
"type": "string"
},
"description": "Field names this task is waiting on — pass one to move_task_answer."
}
},
"required": [
"id",
"title",
"state",
"kind",
"actor",
"due",
"dlabel",
"due_day",
"unlocks"
]
}
},
"moreCount": {
"type": "integer"
},
"blockedReason": {
"type": [
"string",
"null"
],
"description": "no_move / nothing_open / all_in_flight — why there is no next thing."
}
},
"required": [
"hero",
"rows",
"moreCount"
]
}🟢move_task(task_id)
One task on the signed-in person's move: what it is, when it is due, what state it is in, any draft already prepared, and which fields it is waiting on them to answer. Read-only — opening a task leaves no trace. It does not tell you whether the task is in flight: that needs evidence lookups this cheap read skips on purpose. move_tasks is the only place "in progress" appears.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "A task id exactly as move_tasks / move_plan returned it."
}
},
"required": [
"task_id"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"ok": {
"type": "boolean"
},
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"kind": {
"type": "string"
},
"actor": {
"type": "string"
},
"due": {
"type": "integer"
},
"dlabel": {
"type": "string"
},
"due_day": {
"type": "string"
},
"state": {
"type": "string"
},
"draft": {
"type": "object",
"description": "Prepared, never sent."
},
"missing": {
"type": "array",
"items": {
"type": "string"
}
},
"missing_text": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"ok",
"id",
"title",
"kind",
"actor",
"due",
"dlabel",
"due_day",
"state"
]
}🟡move_task_draft(task_id, to)
Prepares one task for the signed-in person and stops. It writes the email or the call script and hands it back; it never sends, dials, submits or pays, and no MCP tool can. The person presses send themselves in PutRoots. It covers email and call tasks, plus a form-filling task that has already been tried and given up on (that falls back to a letter or a call). It cannot start the other two kinds: walk tasks (filling a form on a provider's own site) and research tasks (finding candidates, booking a viewing, filling a rental application) have no execution path here yet and will come back saying the task is neither an email nor a call. Those are done in the PutRoots web app; say so rather than retrying. If it comes back blocked, the task is waiting on a field only the person can answer — use move_task_answer, then call this again.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "A task id exactly as move_tasks / move_plan returned it."
},
"to": {
"type": "string",
"description": "Recipient, when the person supplies one: an email address for an email task, a phone number for a call task. Leave it out to use the recipient we already have."
}
},
"required": [
"task_id"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"ok": {
"type": "boolean"
},
"state": {
"type": "string",
"description": "drafted = ready for them to press send; blocked = waiting on an answer."
},
"draft": {
"type": "object",
"description": "to / subject / body, or the call script. Prepared, not sent."
},
"missing": {
"type": "array",
"items": {
"type": "string"
}
},
"missing_text": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"ok",
"state"
]
}⚪move_task_answer(task_id, field, value)
Fills in one field the signed-in person's task is waiting on (the names come back in missing from move_task or move_task_draft). Only fields that task is actually asking for are accepted, and only values we can store — anything else is refused rather than silently dropped. Pass what the person actually said; never a guess or a plausible default.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "A task id exactly as move_tasks / move_plan returned it."
},
"field": {
"type": "string",
"description": "A field name from the task's missing list."
},
"value": {
"type": "string",
"description": "What the person said. Not inferred, not a placeholder."
}
},
"required": [
"task_id",
"field",
"value"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"ok": {
"type": "boolean"
},
"id": {
"type": "string"
},
"field": {
"type": "string"
},
"state": {
"type": [
"string",
"null"
]
},
"closeout": {
"type": "object"
}
},
"required": [
"ok",
"id",
"field"
]
}🟡move_task_defer(task_id, mode)
later = push it out; it comes back on its own in three days. not_applicable = it doesn't apply to this person; it leaves the list, stops counting against the move, and anything waiting on it can go ahead. undo = put a ruled-out task back. Only on the person's say-so: ruling a task out changes what the rest of the move waits on.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "A task id exactly as move_tasks / move_plan returned it."
},
"mode": {
"type": "string",
"enum": [
"later",
"not_applicable",
"undo"
]
}
},
"required": [
"task_id",
"mode"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"ok": {
"type": "boolean"
},
"state": {
"type": "string"
},
"later_until": {
"type": "integer"
}
},
"required": [
"ok",
"state"
]
}🟢move_events(since, limit)
The signed-in person's move events after an epoch-millisecond timestamp, oldest first — drafted, sent, called, answered, done, skipped. Use it to answer "what changed since we last spoke" without re-reading the whole plan. Capped; more says how many were left out.
Input Schema
{
"type": "object",
"properties": {
"since": {
"type": "integer",
"minimum": 0,
"description": "Epoch milliseconds; 0 for everything."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 500,
"description": "Most recent N of the matches (default 100, max 500)."
}
},
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"ok": {
"type": "boolean"
},
"since": {
"type": "integer"
},
"events": {
"type": "array",
"items": {
"type": "object",
"properties": {
"ts": {
"type": "integer"
},
"type": {
"type": "string"
},
"detail": {
"type": "object"
}
},
"required": [
"ts",
"type"
]
}
},
"more": {
"type": "integer"
}
},
"required": [
"ok",
"since",
"events",
"more"
]
}Community
Evidence