Analytics

papertigerapp.com

An MCP server for PaperTiger that enables paper-trading research and experiments by managing wallets, account context, and performance analysis.

1 endpoint20 known toolsFirst detected September 25, 2026Last detected September 25, 2026

ENDPOINT 1

https://api.papertigerapp.com/mcp

No auth detected

MCP server metadata

Name: papertiger
Version: 1.0.0

Capabilities

tools

Server instructions

PaperTiger is paper trading only. Inspect account context and market-data quality before writes. Use separate wallets for independent hypotheses. Treat reset and delete as destructive. Interpret results with fees, rejected decisions, data quality, and sample size.

Known tools 20

get_capabilities

Use this when the user wants to know which PaperTiger research, paper-trading, experiment, or analysis workflows are available.

Inferred read-only

get_account_context

Use this before account-scoped work to inspect the connected user, wallets, buying power, and application wallet limit.

Inferred read-only

create_wallet

Use this when the user wants an isolated PaperTiger wallet for a paper-trading hypothesis or experiment.

Inferred read-only

update_wallet

Use this when the user wants to rename a specific PaperTiger paper wallet.

Inferred read-only

reset_wallet

Use this only when the user explicitly asks to erase a wallet's paper orders, positions, activities, and performance and restore its starting balance.

Potential side effects

delete_wallet

Use this only when the user explicitly asks to permanently delete a named PaperTiger wallet and its paper-trading history.

Potential side effects

search_markets

Use this to find current public Polymarket or Kalshi markets before creating a hypothesis, paper order, or experiment.

Inferred read-only

resolve_market

Use this when the user supplies an exact Polymarket or Kalshi URL and needs the canonical PaperTiger market identifiers.

Inferred read-only

create_experiment

Use this when the user has a falsifiable paper-trading hypothesis, success criteria, and guardrails that should be tracked independently.

Inferred read-only

create_strategy_version

Use this to attach a new immutable declarative strategy definition and explicit change note to an existing experiment.

Inferred read-only

start_backtest

Use this after checking replayable market-data coverage to run one immutable experiment strategy version over a bounded historical interval.

Inferred read-only

get_run_status

Use this to inspect one backtest or external-paper run and its current deterministic summary.

Inferred read-only

place_paper_order

Use this only when the user asks to place a simulated PaperTiger order using canonical venue market and outcome identifiers.

Inferred read-only

cancel_paper_order

Use this when the user asks to cancel one open simulated PaperTiger order.

Inferred read-only

explain_trade

Use this to inspect one PaperTiger paper order, its immutable fills, execution prices, fees, rejection state, and timestamps.

Inferred read-only

get_data_quality

Use this before a backtest to inspect replayable coverage, fidelity, gaps, and intentional sampled intervals.

Inferred read-only

analyze_run

Use this to retrieve PaperTiger's deterministic rejection funnel, execution counts, fee decomposition, net P&L, and evidence qualifications for one run.

Inferred read-only

get_rejection_funnel

Use this when diagnosing zero or few trades; it returns server-counted candidates, qualifications, submissions, fills, and rejection reasons.

Inferred read-only

compare_runs

Use this to compare two to ten compatible PaperTiger runs using server-calculated funnels, execution, fees, and net results.

Inferred read-only

export_research_bundle

Use this to retrieve one bounded JSON research bundle containing the experiment, immutable strategy, run, decisions, and deterministic analysis.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.papertiger]
url = "https://api.papertigerapp.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "papertiger": {
      "type": "http",
      "url": "https://api.papertigerapp.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: papertiger
Remote MCP URL: https://api.papertigerapp.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "papertiger": {
      "url": "https://api.papertigerapp.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "papertiger": {
      "type": "http",
      "url": "https://api.papertigerapp.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "papertiger",
  "transport": "streamable-http",
  "url": "https://api.papertigerapp.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.