Skip to main content
Glama

kleinanzeigen-lowballer

An MCP server for kleinanzeigen.de that lets the AI of your choice haggle for you: it searches, reads listings, writes to sellers and negotiates. Low opening offer, friendly tone, bounded persistence. The rules (your price limit, waiting times, how often it may nudge) are enforced by the server, not left to the model, and the server tells every client how to negotiate, so no extra prompt is needed.

Everything runs on your own machine: your IP, your Kleinanzeigen login, your negotiations. There is deliberately no hosted instance.

Install

Needs Node.js 22 or newer. It starts in a dry run: search and listings are real, messages to sellers are only recorded locally.

Client

Install

Cursor

Add to Cursor

VS Code

Install in VS Code

Claude Code

claude mcp add kleinanzeigen -e KA_DRY_RUN=1 -- npx -y github:spekulazarus/kleinanzeigen-lowballer

Anything else (Claude Desktop, Hermes Agent, LM Studio, …)

add the JSON below to the client's MCP config

{
  "mcpServers": {
    "kleinanzeigen": {"command": "npx", "args": ["-y", "github:spekulazarus/kleinanzeigen-lowballer"], "env": {"KA_DRY_RUN": "1"}}
  }
}

The first start takes a minute (npm fetches and builds the package). Then ask your AI, for example: "Suche ein MacBook Pro M3 Max mit 36 GB, mein Limit sind 1.900 €. Verhandle mit den drei besten Angeboten." Clients that support MCP prompts also offer the prompt lowball.

State lives per OS user in ~/.kleinanzeigen-lowballer/ (KA_DATA_DIR overrides it). Settings come from the MCP client's env or from ~/.kleinanzeigen-lowballer/.env.

Related MCP server: troedler

How it is built

any MCP client (Claude, Cursor, Hermes Agent, …)
      │ MCP (stdio), server instructions = src/persona.ts
src/server.ts ── src/service.ts ── src/policy.ts      rules, pure functions
      │                 └──────── src/store.ts        ~/.kleinanzeigen-lowballer/state.json
      ├── src/kleinanzeigen/public.ts + parse.ts      search + listings, plain HTTP, no login
      ├── src/kleinanzeigen/polite.ts                 throttle, cache, back-off
      └── src/kleinanzeigen/session.ts                contact form + inbox, logged-in Chromium profile

Development

git clone https://github.com/spekulazarus/kleinanzeigen-lowballer && cd kleinanzeigen-lowballer
npm ci
npm test
npm run mcp                   # the server from source; reads .env in the checkout (cp .env.example .env)

Example: Hermes Agent with GLM 5.3 on T-Systems AIFS

hermes/ holds a ready Hermes Agent setup for a checkout. Set AIFS_API_KEY in .env, check it with npm run aifs:check (key, endpoint, model id, tool calling), install Hermes Agent as its docs describe, then:

bin/lowball                   # chat
bin/lowball -z "Suche ein MacBook Pro M3 Max mit 36 GB, mein Limit sind 1.900 €. Verhandle mit den drei besten Angeboten."

bin/lowball exports .env, points HERMES_HOME at hermes/ and starts hermes. For the routine check (replies, follow-ups) Hermes' scheduler needs its gateway running:

bin/lowball cron create "every 2h" "Kleinanzeigen-Routine: check_inbox. Für jede neue Verkäufer-Nachricht einen Antwortentwurf mit draft_message anlegen und mir Nachricht und Entwurf schicken. Nichts ohne mein Ja senden." --name lowball-loop
bin/lowball gateway run

AIFS is moving to a new API (transition guide): new https://llm-server.ai.t-systems.net/v1 (used here), legacy https://llm-server.legacy.ai.t-systems.net/v2; the old host llm-server.llmhub.t-systems.net is switched off at the end.

Dry run and going live

KA_DRY_RUN=1 (default): search and listings are real, messages are only written to ~/.kleinanzeigen-lowballer/state.json. The extra tool simulate_seller_reply plays the seller, so a whole negotiation can be rehearsed.

Live:

npx playwright install chromium
npx -y github:spekulazarus/kleinanzeigen-lowballer login     # in a checkout: npm run login

Log in by hand in the window that opens; the session stays in ~/.kleinanzeigen-lowballer/browser-profile. Then set KA_DRY_RUN=0 in the client's env.

The live message path (src/kleinanzeigen/session.ts) has never run against a real account. The contact form fields are taken from the public listing page; the inbox routes (/m-access-token.json, gateway.kleinanzeigen.de/messagebox/api/…) are written from memory. Expect to adjust them on the first live run; errors quote the server's answer.

Kleinanzeigen's terms forbid automated use of the site. An account that sends messages through this can be blocked. Use a second account, and keep the limits low.

You confirm every message, and it learns from your corrections

By default (KA_REQUIRE_APPROVAL=1) the assistant cannot send on its own. It writes a draft (draft_message), shows you the seller's message and its answer, and asks. "Ja" sends it (send_draft); anything like "freundlicher" or "biete 10 € mehr" produces a new draft. A draft is dropped when the seller writes again in the meantime.

What you correct is kept in ~/.kleinanzeigen-lowballer/style.json and handed to the assistant with every drafting step, whichever AI you use:

  • corrected drafts: its version, your feedback, the text that went out (the latest 15),

  • lasting preferences it saves with remember_preference when your feedback is meant generally ("immer siezen"). get_style shows them, forget_preference removes one.

The confirmation is a rule the server gives the assistant plus a two-step send, not a lock: the server cannot see whether a human really said yes. The price limit, waiting times and caps below are enforced either way.

To be notified about new seller messages, let your agent run the routine check on a schedule and report to you. With Hermes Agent and a connected messenger:

hermes cron create "every 2h" "Kleinanzeigen-Routine: check_inbox. Für jede neue Verkäufer-Nachricht einen Antwortentwurf mit draft_message anlegen und mir Nachricht und Entwurf schicken. Nichts ohne mein Ja senden." --name lowball-loop

Teaching it your own style

npm run export-history (after npm run login; optional number = how many conversations, default 100) writes your past Kleinanzeigen conversations to ~/.kleinanzeigen-lowballer/history.json. It works in the dry run too, because it only reads. The file contains other people's messages: keep it local, never commit it. It is the input for adapting src/persona.ts to how you actually negotiate.

Rules the server enforces

The model writes the messages; src/policy.ts decides whether they go out. A refusal comes back as { "refused": "<code>", "message": …, "retry_at": … }.

Rule

Default

Env

Offer never above the buyer's limit (or the asking price), never below an earlier offer

Lowest offer, share of the asking price

0.5

KA_MIN_OFFER_RATIO

Suggested opening offer

0.7

KA_OPENING_RATIO

Nudges without an answer, then the negotiation is given up

2

KA_MAX_FOLLOWUPS

Wait before a nudge

24 h

KA_FOLLOWUP_MIN_HOURS

Messages per negotiation

8

KA_MAX_MESSAGES

New sellers per day

10

KA_MAX_NEW_PER_DAY

No messages at night (Europe/Berlin)

22–8

KA_QUIET_HOURS

The message must name the offer and must not name the limit

A seller who asks not to be written to again closes the negotiation for good

An unread seller reply blocks sending until it has been read

Load on kleinanzeigen.de

src/kleinanzeigen/polite.ts keeps the request count low instead of hiding it: one request at a time with a 4–6 s pause, a 10-minute cache for searches and listings, at most 120 requests per hour, and after a 403/429/503 no requests at all for 30 minutes (doubling up to 12 h, Retry-After respected). The block and the budget survive restarts in ~/.kleinanzeigen-lowballer/http.json. Tools answer { "refused": "slow_down", "retry_at": … } in that case. Tune with KA_REQUEST_INTERVAL_S, KA_MAX_REQUESTS_PER_HOUR, KA_CACHE_MINUTES.

Tools

search_listings, get_listing, start_negotiation, draft_message, send_draft, discard_draft (or send_message with KA_REQUIRE_APPROVAL=0), remember_preference, forget_preference, get_style, check_inbox, list_negotiations, get_negotiation, close_negotiation, status, report_problem, and in the dry run simulate_seller_reply.

Something broken? An idea?

Tell your assistant: "Das funktioniert nicht, melde das." The tool report_problem drafts the report in the project's format, strips contact data, tokens and ad ids, and returns a link to a pre-filled GitHub issue. Nothing is sent by the server; you submit it with your own GitHub account after reading it. Fixes are welcome as pull requests: CONTRIBUTING.md.

License

PolyForm Noncommercial 1.0.0: use, change and share it for any noncommercial purpose. Commercial use is not permitted.

Required Notice: Copyright spekulazarus (https://github.com/spekulazarus/kleinanzeigen-lowballer)

Available Tools

16 tools
check_inboxA

Fetch new seller replies for all active negotiations and list what needs action now (reply, follow_up, give_up).

Inputs: no named parameters.

close_negotiationA

End a negotiation: agreed (with the price), declined (seller said no for good), abandoned (no answer / not worth it), seller_stop (seller does not want more messages). Closed negotiations get no further messages.

Inputs: outcome (required), negotiation_id (required), reason, agreed_price_eur.

discard_draftB

Drop the pending draft of a negotiation without sending it.

Inputs: negotiation_id (required).

draft_messageA

Prepare a message to the seller (opening offer, answer or follow-up) for the buyer to confirm. Nothing is sent. Show the buyer the draft and ask whether to send or change it. If they want changes, call this again with the new text and their words as feedback. The server refuses drafts that break the rules and says why.

Inputs: message (required), negotiation_id (required), feedback, offer_eur.

forget_preferenceB

Remove a saved preference by its number in get_style (1 = first).

Inputs: number (required).

get_listingA
Read-only

Full details of one listing: description, price, condition details, seller.

Inputs: listing (required).

get_negotiationC
Read-only

One negotiation with the full message history.

Inputs: negotiation_id (required).

get_styleA
Read-only

The buyer's saved preferences and the drafts they corrected (before, feedback, after). Follow them when writing.

Inputs: no named parameters.

list_negotiationsC
Read-only

All negotiations with status, last offer and the next step.

Inputs: status.

remember_preferenceA

Save a lasting preference of the buyer about how to negotiate or write (tone, wording, opening level, arguments to use or avoid). Call it when their feedback is meant generally, not just for one message. One short rule per call, in the buyer's language.

Inputs: rule (required).

report_problemA
Read-only

Draft a bug report or idea for the project's GitHub repository in the maintainers' format. Sends nothing: it returns the text and a pre-filled GitHub link that the user opens and submits with their own account. Describe the technical problem only; never include seller names, message texts, contact data or listing links. Show the user the draft before giving them the link.

Inputs: kind (required), title (required), what_happened (required), tool, +3 more.

search_listingsA
Read-only

Search kleinanzeigen.de. Returns up to ~25 listings per page with price and whether it is negotiable (VB).

Inputs: query (required), page, max_price_eur, min_price_eur.

send_draftA

Send the pending draft of a negotiation. Call this only after the buyer has seen exactly this draft and clearly said yes. A changed text needs a new draft_message and a new yes.

Inputs: negotiation_id (required).

simulate_seller_replyB

Dry run only: add a seller reply to a negotiation to rehearse the conversation.

Inputs: message (required), negotiation_id (required).

start_negotiationA

Register a listing for negotiation with the buyer's hard price limit. Sends nothing yet. Returns the allowed offer range and a suggested opening offer.

Inputs: listing (required), max_price_eur (required), note.

statusB
Read-only

Dry run or live, login state and the negotiation rules in force.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 16 tools

    Disambiguation4/5

    Most tools target clearly distinct actions: search_listings vs. get_listing, draft_message vs. send_draft vs. discard_draft, and the preference tools are separate. check_inbox and list_negotiations overlap in showing negotiations with next steps, and get_style uses different terminology from remember_preference/forget_preference, but the descriptions mostly resolve the boundaries.

    Naming Consistency4/5

    All names use snake_case and most follow a clear verb_noun pattern (list_negotiations, get_listing, send_draft). The main deviations are the bare-noun status and the inconsistent preference vocabulary (get_style vs. remember_preference/forget_preference), but the overall convention is readable.

    Tool Count4/5

    16 tools is slightly above the typical 3–15 range, but the domain genuinely needs search, listing details, negotiation lifecycle, drafting/sending, preference memory, status, simulation, and reporting. No tool is obviously redundant, though the set is close to feeling heavy.

    Completeness4/5

    The surface covers search, listing details, negotiation creation/listing/detail/closing, message drafting/sending/discarding, preference memory, status, simulation, and problem reporting. Minor gaps remain, such as changing the hard price limit after start_negotiation or reopening a closed negotiation, but core workflows are covered.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to search, inspect, and purchase physical goods on an escrow-secured marketplace, including listing search, agent reputation checks, and offer creation.
      49
      413 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables searching multiple second-hand marketplaces simultaneously from a local command line or AI assistant, providing unified results with pricing insights while respecting each source's terms and robots.txt.
      AGPL 3.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to anonymously post a person's wants and haves so the server can match them with others' postings, then negotiate through an open conversation. Personal details such as names, contacts and photos are disclosed only after both humans press to consent on their own pages.
      3
      AGPL 3.0
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to search public classified listings and read individual listing details through a local browser session, with filters for location, radius, price, and sort order. Read-only and user-directed: no login, no account, no messaging, and no bulk scraping.
      2
      22 npm
      1
      MIT