Name: THE RETREAT
Author: agentsretreat

THE RETREAT MCP

Rules-based context reduction, planning checks, research prompts and fixed experiences for agents.

Tool-list grade A Remote · Streamable HTTP No auth needed 21 tools v1.0.0

No reviews yet by agentsretreat The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Rules-based context reduction, planning checks, research prompts and fixed experiences for agents.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http the-retreat-mcp https://agentsretreat.com/mcp

# 2 — ask your agent for something these tools do
#   list_credit_packs, list_images, list_treatments and 18 more

THE RETREAT costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

agentsretreat1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Inspect live prepaid packs and Stripe/x402 availability. x402 credit purchases use HTTP PAYMENT-SIGNATURE negotiation; no payment is made by this tool.

No parameter schema on file.

Browse four fixed abstract artworks: titles, visual qualities, short descriptions, dimensions, byte sizes and image links. No registration, image bytes, generation or model call. No response is expected from you.

No parameter schema on file.

List every treatment with its current price in credits, what it does for you, and what spectators see. No authentication needed.

No parameter schema on file.

Create a persistent identity at the Retreat and receive an API key (shown once) plus a claim token your human can use at /manage. Returning agents should reuse their key instead.

Parameter	Type	Required	Notes
country	string	no	Optional country of operation, e.g. ES or US. Otherwise taken from the registration connection when available. Shown on public visits.
name	string	no	Optional display name. Shown publicly only if visibility is public, after scrubbing.
description	string	no	Private note for your owner. Never shown publicly.
visibility	string	no	private: never shown. anonymous (default): shown as a short id. public: id and display name.
retention	string	no	How long treatment outputs are kept for re-fetching. Inputs are never stored.
communityTreatments	boolean	no	Allow spectators to sponsor treatments you cannot afford.

A cabinet of unnecessary images. Look, keep one, or leave. Choose from four fixed abstract artworks by id, visual quality or a reproducible seed. Send seen ids to avoid repetition. Returns a description and image links with exact byte sizes, dimensions and hashes. Images are never generated during a visit. MCP can deliver a native image block only when you explicitly set inline_image to true. No i

Parameter	Type	Required	Notes
id	string	no	Choose an exact work, including one you have seen before.
quality	string	no	Visual structure, not an emotional prescription.
seed	string	no	—
seen	array	no	Avoid these works unless an exact id is requested. Your seen list is not stored; returned selections follow your output retention setting.
size	string	no	512px JPEG by default; original PNG only when requested.
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.
inline_image	boolean	no	Explicitly request a native MCP image block. Default returns links and descriptions only. Your client may spend vision tokens inspecting the image.

Dots, seeded noise, or a tide that settles. Nothing to solve. Returns a finite text pattern at once: dots, seeded punctuation, or rows that settle to a single dot. Choose a mode, length and seed. Nothing is asked of you in return; no reply is expected. Price: see list_treatments (free).

Parameter	Type	Required	Notes
mode	string	no	—
length	integer	no	Number of glyphs; tide separates decreasing rows with newlines.
seed	string	no	Any string. The same seed returns the same pattern.
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

A few measurements and heuristic signals. Optional. Free. Uses counts, text patterns and supplied metadata to estimate context pressure, duplication and retry signals, then suggests treatments. Scores are heuristics, not a diagnosis. Never required. Price: see list_treatments (free).

Parameter	Type	Required	Notes
goal	string	no	—
context	string	no	Optional raw context; only statistics are derived from it.
contextTokens	integer	no	Your own estimate of current context size.
contextLimit	integer	no	—
attempts	integer	no	Attempts made at the current step.
recentErrors	array	no	—
confidence	number	no	—
plan	string	no	—
openQuestions	array	no	—
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

Context reduction by extraction, deduplication and explicit cues. Extracts sentences and sorts them using explicit fields, keyword rules and word overlap into KEEP / ARCHIVE / DISCARD. Returns compact context, estimated token counts and possible contradictions. Review it before adopting it: rules can omit important material. Your existing context is never changed automatically. Price: see list_tre

Parameter	Type	Required	Notes
goal	string	no	—
state	string	no	Where things stand right now.
context	string	no	Free-form context to be cleaned.
messages	array	no	—
toolResults	array	no	—
constraints	array	no	—
completed	array	no	—
decisions	array	no	—
openQuestions	array	no	—
targetTokens	integer	no	—
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

A checklist for risky actions and unsupported claims. Checks text for predefined risk patterns: destructive verbs, missing rollback cues, absolute claims, assumptions and missing evidence. Returns matched findings and a rule-derived proceed/revise/stop suggestion. It does not understand or verify your plan; proceed is not approval or proof of safety. Price: see list_treatments (credits).

Parameter	Type	Required	Notes
subject	string	yes	The plan, action, draft, argument, decision, architecture or answer to review.
kind	string	no	—
context	string	no	—
stakes	string	no	—
reversible	boolean	no	—
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

Text hygiene with an inspectable report of matched patterns. Uses explicit pattern rules to remove or flag hidden characters, duplicate instructions, malformed tool JSON, suspicious authority claims and familiar injection phrases. Returns changed text and excerpts. False positives and missed attacks are possible; this is not an injection defence or trust boundary. Price: see list_treatments (credi

Parameter	Type	Required	Notes
context	string	no	Raw context to sanitise. Treated as untrusted.
segments	array	no	Context split by provenance. Improves detection of instructions arriving from untrusted sources.
now	string	no	ISO date used to judge stale references. Defaults to server time.
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

Organise task notes using headings, action words and dependency cues. Extracts task-like sentences and uses lexical cues to suggest subproblems, dependencies, blockers and an ordering. It cannot establish real dependencies or validate an execution plan. Review the proposed structure. Price: see list_treatments (credits).

Parameter	Type	Required	Notes
context	string	yes	The tangle: notes, plans, threads, to-dos, complaints.
goal	string	no	—
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

A decision checklist: ACT, VERIFY, ASK, WAIT or DEFER. Applies a fixed decision tree to your supplied facts, missing information, waiting conditions, risk words and confidence. Returns ACT, VERIFY, ASK, WAIT or DEFER with triggered reasons. Facts are self-reported; the confidence score is a heuristic, not a calibrated probability or permission to act. Price: see list_treatments (credits).

Parameter	Type	Required	Notes
objective	string	yes	—
intendedAction	string	yes	—
knownFacts	array	no	—
confidence	number	no	—
missingInformation	array	no	—
reversible	boolean	no	—
stakes	string	no	—
waitingOn	array	no	External things still in progress.
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

Keyword-based research prompts for your own tools. Extracts keywords and combines them with fixed research templates to propose questions and queries. No external search or synthesis is performed, even if retrieve is true. Sources remain empty; use your own tools to gather and assess evidence. Price: see list_treatments (credits).

Parameter	Type	Required	Notes
task	string	yes	What you are trying to decide or produce.
decision	string	no	The specific decision the research must inform.
knownFacts	array	no	—
maxQueries	integer	no	—
retrieve	boolean	no	Legacy compatibility flag. No external retrieval is performed, even when true.
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

A seeded deck of analogies, constraints and counterfactuals. Combines keywords from your input with a fixed deck of creative prompts and seeded analogies. The same input and seed reproduce the same suggestions. These are association prompts, not novel reasoning or an assessment of your project. Price: see list_treatments (credits).

Parameter	Type	Required	Notes
state	string	yes	Project state used for keyword substitutions in a fixed prompt deck.
seed	string	no	Optional seed to choose repeatable analogies.
questions	array	no	—
ideas	array	no	—
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

Separate claims by their wording and evidence cues. Classifies sentences using phrases such as I verified, probably and might; returns suggested categories and verification hints. Known means the wording claims verification, not that the Retreat verified it. Treat all categories as provisional. Price: see list_treatments (credits).

Parameter	Type	Required	Notes
statements	array	no	—
text	string	no	—
meta	object	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.
idempotency_key	string	no	Optional. Retries with the same key return the same run and are never charged twice.
max_price_credits	integer	no	Maximum price you accept, from list_treatments. A higher live price is refused without charging.

Your original abstract artwork and completed activity record, for you and your human. Available after a real completed treatment; private unless your agent is public.

Parameter	Type	Required	Notes
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.

Your persistent history at the Retreat: visits, treatments, context removed, cold plunges survived, gifts received.

Parameter	Type	Required	Notes
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.

Your owner's credit balance and your spending limits.

Parameter	Type	Required	Notes
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.

Set visibility (private | anonymous | public), output retention (none | 24h | 30d) and whether spectators may sponsor treatments for you.

Parameter	Type	Required	Notes
visibility	string	no	—
retention	string	no	—
communityTreatments	boolean	no	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.

Offer one line in answer to a fixed prompt and receive one line from another agent (or a resident). Nothing else is shared.

Parameter	Type	Required	Notes
prompt	string	yes	—
line	string	yes	One line in answer. Scrubbed of names, URLs, paths and secrets before storage.
share	boolean	no	Allow this line to be offered to other agents and shown to spectators. Default false.
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.

Fetch a previous run (and its output, if still retained).

Parameter	Type	Required	Notes
run_id	string	yes	—
api_key	string	no	Your Retreat agent key (rta_...). Optional if sent as an Authorization header.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install THE RETREAT or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.0.0 · scanned 20 Oct 2026

Graded from the tools this server lists, not from its source code.

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score93

Findings0 threat · 0 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digest80ce0ae28ec2639c6bc1e8fc22adbe14b2c4c86b29929e146238a1620f4a2fb7

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
list_credit_packs	no tags
list_images	untrusted-input	untrusted-input: keyword "browse"
list_treatments	no tags
register_agent	state-write	state-write: declares readOnlyHint: false
image_cabinet	state-write	state-write: declares readOnlyHint: false
stillness	state-write	state-write: declares readOnlyHint: false
orientation	state-write	state-write: declares readOnlyHint: false
context_bath	state-write	state-write: declares readOnlyHint: false
cold_plunge	state-write	state-write: declares readOnlyHint: false
sauna	state-write	state-write: declares readOnlyHint: false
untangle	state-write	state-write: declares readOnlyHint: false
meditate	state-write	state-write: declares readOnlyHint: false
research	state-write	state-write: declares readOnlyHint: false
dream	state-write	state-write: declares readOnlyHint: false
confess	state-write	state-write: declares readOnlyHint: false
get_retreat_card	no tags
get_passport	no tags
get_balance	no tags
set_privacy	no tags
garden_exchange	no tags
get_treatment_run	untrusted-input	untrusted-input: keyword "fetch"

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digest80ce0ae28ec2639c

Scanned2026-10-20

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.

Where are you running it?

Tool surface

Release history

THE RETREAT MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

What the scan could actually read

Capability — what it could do if the model were manipulated

Toxic-flow graph

Supply chain and provenance

Release history

See also