polymarket-mcp-server

Overview Schema Source Related Servers Discussions Admin

Open a SIMULATED (paper) Polymarket bet

polymarket_paper_open

Record a simulated bet in a local paper-trading ledger to track and score a prediction hypothesis without real money; fills at the executable ask plus category taker fee.

Instructions

Record a SIMULATED bet in the local paper-trading ledger. No real money, no order is placed — this only writes a local file to track a hypothesis and score it later.

Fills honestly at the executable ASK plus the category taker fee (Polymarket charges takers since 2026-03-30), so the simulated P&L isn't a fantasy. Prefer slug + outcome so the conditionId is captured for auto-scoring at resolution.

Args:

token_id (string, optional) OR slug (string) + outcome (string).
size_usdc (number): simulated stake (virtual money).
p_estimate (number 0-1, optional): your probability for this outcome (for Brier scoring + the Kelly hint).
category ('crypto'|'sports'|'politics'|'macro'|'geopolitics'|'other'): taker-fee bucket.
note (string, optional): the hypothesis you're testing.

Returns: the recorded bet + a fractional-Kelly sizing hint (full & half) + the virtual bankroll.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`note`	No	Optional note, e.g. the hypothesis being tested.
`slug`	No	Market slug — alternative to token_id. Combine with 'outcome'.
`outcome`	No	Outcome name to select when using 'slug' (e.g. 'Yes' or 'No'). Defaults to the first outcome.
`category`	No	Category for the taker-fee model (crypto highest, geopolitics free).	other
`token_id`	No	CLOB token id (the ~77-digit id for ONE outcome). Preferred when you already have it.
`size_usdc`	Yes	SIMULATED stake in USDC (virtual money — no real trade is placed).
`p_estimate`	No	Your probability estimate 0-1 for this outcome (used later for Brier/calibration scoring).
`response_format`	No	Output format: 'markdown' (concise, human-readable; default) or 'json' (full structured data).	markdown

Output Schema

TableJSON Schema

Name	Required	Description	Default
`bet`	Yes
`bankroll`	Yes
`kellyFull`	Yes
`kellyHalf`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Sep 28, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations already declaring the mutation/safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), the description adds real behavioral detail beyond them: no order is placed, only a local file is written, fills occur at the executable ASK plus the category taker fee (dated 2026-03-30), and auto-scoring is set up via conditionId. It stops short of disclosing duplicate-token_id behavior or overwrite semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is reasonably front-loaded, but the Args block duplicates the already-complete schema and the simulation caveat is stated twice ("No real money, no order is placed" and "only writes a local file"), which exceeds what earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no elaboration, and for a local 8-parameter write tool the description covers the key facts (simulated nature, fill/fee model, preferred identifier pair). Minor gaps remain, such as duplicate-bet handling and whether repeated calls accumulate or overwrite.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter's meaning; the description's Args section largely restates that. The only genuine additions are the token_id-vs-slug+outcome precedence and the auto-scoring rationale for preferring slug+outcome, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Record a SIMULATED bet in the local paper-trading ledger") and immediately scopes it against reality ("No real money, no order is placed"), which cleanly distinguishes it from sibling read tools and from paper_close/paper_delete.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description conveys the context (track a hypothesis and score it later) and gives argument-level preference ("Prefer slug + outcome..."), but it never states explicit when-to-use/when-not conditions nor names an alternative sibling to route to, so the usage guidance is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.