Skip to main content
Glama

loophole-tape

by io.github.gosadu
OverviewDiscussionsAdmin

Robinhood Chain new memecoin launches ($0.01)

rhc_recent_launches
Read-onlyIdempotent

$0.01 USDC per call. Use to screen or poll new pons memecoin launches on Robinhood Chain (4663), optionally ring-shaped ones only; one token's full risk card is GET /v1/rhc/curve/{address}. Not for Solana. Optional args: limit (1-200, default 50), max_age_s (30-21600, default 3600), pair ('any' | 'eth'), only_live (bool), min_buys (int), ring_only (bool), since (unix seconds cursor). Recent pons memecoin launches on Robinhood Chain (chain 4663; default last hour, newest first) as compact structure cards: raised (ETH), progress to the 4.2 ETH graduation, price multiple vs launch (exact curve reserves), the launch's trade fee and creator tax in bps (fees.creator_tax_bps: 0-1900, chosen by the creator, charged on every buy and sell), snipe-tax activity, holder concentration (top-1 / top-5 / HHI), same-block direct-buy cluster share (matching timing, not proof of coordination), terminal-vs-direct route mix with the terminal router transactions joined to their wallets, inflow (new buyers in the last 2 / 6 s), lifecycle (live / complete / graduated). Every card carries a ring block: the RING SCREEN flags the coordinated-cluster structure our own capture measured (unique_buyers >= 8 and same-block direct-buy cluster share >= 0.5); ring_only=true returns just those curves, and the response carries the rule with its measured base rates (14.5% of launches, 47% dumped, median 0.37x terminal in the 2026-09-06/07 window) so you can price the flag yourself. Matching timing is not proof of coordination. Filter pair=eth for ETH-paired curves or min_buys for a minimum observed activity count. Poll with since= to receive only launches you have not seen, oldest first. Each item also carries verdict (avoid / caution / no_flags_observed) and basis, the rule ids of the fixed public rule (LABELS rhc_verdict at /v1/labels) that fired; the curve card gives each reason with its evidence and base rate. Returns JSON envelope with data{count, items[compact structure cards, each with verdict and basis by the public rule], ring_rule} (+ next_cursor, truncated with since).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pairNo'any' or 'eth' (ETH-paired curves only)any
limitNomax items 1-200
sinceNounix seconds cursor (next_cursor of the previous call): launches after it, oldest first
min_buysNominimum curve buys observed
max_age_sNoonly launches within this many seconds (30-21600)
only_liveNodrop completed / graduated curves
ring_onlyNoring screen: only curves matching the measured coordinated-cluster structure (unique_buyers >= 8 and same_block_direct_cluster_share >= 0.5)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / ring_only
      Added value: +{
+  "default": false,
+  "description": "ring screen: only curves matching the measured coordinated-cluster structure (unique_buyers >= 8 and same_block_direct_cluster_share >= 0.5)",
+  "title": "Ring Only",
+  "type": "boolean"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / since
      Added value: +{
+  "anyOf": [
+    {
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "unix seconds cursor (next_cursor of the previous call): launches after it, oldest first",
+  "title": "Since"
+}
  3. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, and the description does not contradict them. It adds substantial behavioral context: cost per call, fee/tax mechanics (creator_tax_bps 0-1900), clustering caveat ('Matching timing is not proof of coordination'), the ring screen rule and its measured base rates, verdict logic, and the response envelope structure. This goes far beyond the annotation baseline.

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 densely informative, front-loading the cost and core purpose before diving into details. It is well-structured with clear sections (filters, response contents, rule explanation). Though verbose, every sentence adds value; a 4 reflects the length, not wasted words.

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?

For a 7-parameter tool with no output schema, the description is exceptionally complete: it explains all filters, the exact response envelope (data.count, items, ring_rule, next_cursor), the meaning of each card field, the rule logic, and how to paginate. Nothing an agent needs to invoke it correctly is missing.

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?

Schema description coverage is 100% and the description adds meaning beyond it: it explains ring_only's rule and effect, since as a cursor for pagination, pair=eth filtering, min_buys as activity threshold, and the meaning of the returned fields (e.g., cluster share, terminal-vs-direct route mix). It enriches every parameter with operational context that the schema alone does not provide.

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 (screen/poll) and resource (new pons memecoin launches on Robinhood Chain, chain 4663), and differentiates from Solana launches and the per-token risk card via explicit references. The scope is unambiguous and distinct from siblings like recent_launches (Solana) and rhc_curve_card.

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 when-to-use (screen or poll new launches) and when-not ('Not for Solana'), plus a pointer to the alternative for a single token (GET /v1/rhc/curve/{address}). Also explains how to poll incrementally with since=<next_cursor> and how to filter with ring_only, pair, and min_buys. Clear routing among siblings.

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

All loophole-tape toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources