Skip to main content
Glama

Packagist

by io.github.pipeworx-io

Polymarket Arbitrage

polymarket_arbitrage
Read-onlyIdempotent

Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a trending_scan of the top ~200 markets by weekly volume; pass event for the strongest per-event partition_check, or topic for a themed cross-event scan. event (recommended for a specific market): pass a Polymarket event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k"; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). topic (for cross-event scanning): pass a seed question like "Strait of Hormuz traffic returns to normal" or "Fed rate decision"; searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}. FILL CHECK: when the partition signal fires, arbitrage.fill_check prices it against live CLOB depth (theoretical_edge_pp_at_book vs realizable_edge_pp at 1000 shares/leg, thin_legs[]) — realizable_edge_pp ≤ 0 means the overround exists only at last-trade, not in the book; do not trade it. For custom sizing use polymarket_fill_risk.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
eventNoSingle-event mode (use this if you know the specific Polymarket event): event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k". Full Polymarket URLs also accepted.
topicNoCross-event mode (use this if you want to scan related events across the platform): a topic or seed question like "Fed rate decision" or "Strait of Hormuz traffic returns to normal". Tool searches Polymarket for related events and checks monotonicity across them.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description goes beyond by detailing internal logic: semantic anchor (Jaccard similarity ≥0.30), partition filter (placeholder slug detection, >20% placeholder fraction returns null), and fill check that prices against live order book, warning not to trade if not realizable. This provides comprehensive behavioral transparency.

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

Conciseness4/5

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

The description is long but well-structured, starting with a clear purpose, then detailing modes, internal filters, fill check, and return structure. Every paragraph adds valuable information, though some internal details could be condensed. Overall, it is appropriately detailed given the tool's complexity.

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

Completeness5/5

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

Despite lacking an output schema, the description thoroughly explains the response format (opportunities array with fields, partition_check object, fill check results) and edge cases (null signals when placeholder fraction too high). It also mentions the return of 'skipped_low_similarity' and 'thin_legs[]'. This makes the tool's behavior fully predictable.

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

Parameters5/5

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

Both parameters have 100% schema description coverage, but the description adds significant context: examples of values (e.g., 'fed-decision-may-2026' for event, seed questions for topic), explanation of how each parameter affects scanning behavior, and internal logic like semantic anchor and partition filter. This exceeds the schema's basic descriptions.

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?

The description clearly states the tool finds arbitrage opportunities via monotonicity violations and partition-sum checks. It distinguishes between modes (no args, event, topic) and explains what each mode does, making it easy for an agent to understand the tool's purpose relative to siblings like polymarket_edges or polymarket_fill_risk.

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

Usage Guidelines5/5

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

Provides explicit guidance on when to use each parameter (event for a specific market, topic for cross-event scans) and recommends defaults. It explains the difference between modes and when cross-event scanning catches patterns single-event misses. Also mentions custom sizing via polymarket_fill_risk, giving clear usage context.

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

All Packagist toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.3/5.0
Disambiguation2/5

Many tools have overlapping purposes: ask_pipeworx_beta is a literal duplicate of ask_pipeworx, and ai_visibility_check/scans overlap with each other while the many prediction-market and edge tools cover similar ground. The verbose descriptions help somewhat, but an agent would frequently struggle to pick the right tool.

Naming Consistency2/5

Naming is inconsistent: some tools use verb_noun (get_package, list_versions), others noun_verb (ai_visibility_check, bet_research), and several are brand-specific (pipeworx_feedback, pipeworx_trending) with no uniform verb style. The mixed patterns make it hard to predict tool names.

Tool Count1/5

35 tools is far too many for a server named Packagist: only 4-5 tools relate to the PHP/Composer registry while the vast majority concern Pipeworx data lookups, Polymarket analysis, and memory utilities. The scope is severely mismatched with the server's name and apparent purpose.

Completeness2/5

For a Packagist registry server, the core read operations (search, get, list versions, stats) are present, but the server is cluttered with unrelated functionality and offers no package management actions. The tool set is not complete for any single, coherent domain, making it feel like two different servers merged into one.

Resources