Agent Margin Router

arXiv Search

arxiv_search

Read-only

Search arXiv preprints: returns id, title, authors, abstract, categories, published/updated dates and PDF links, sortable by relevance or date, optionally filtered by category (e.g. cs.AI). Pay per call with USDC or USDT on Base via x402. 3 free calls per wallet.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "arxiv_search"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	Free-text search query.
`wallet`	No	Your EVM wallet address (0x...). Unlocks the free tier (3 free calls per wallet).
`api_key`	No	Optional AMR enterprise API key.
`sort_by`	No	Sort order (default relevance).	relevance
`category`	No	Optional arXiv category, e.g. cs.AI.
`x_payment`	No	Optional signed x402 payment payload (base64 JSON) for USDC/USDT on Base.
`max_results`	No	1-50 (default 10).

Output Schema

Name	Required	Description	Default
`query`	Yes
`token`	No	Token actually used for payment (USDC, USDT or FREE).	USDC
`papers`	Yes
`source`	Yes
`routing`	Yes	How the request was routed (provider, fallback, cache, latency).
`sort_by`	Yes
`category`	No
`cost_usdc`	Yes	Price charged in stablecoin units (USDC/USDT 1:1); 0 on the free tier.
`fetched_at`	No	UTC timestamp when the data was fetched.
`attribution`	No
`paper_count`	Yes
`total_results`	No
`freshness_seconds`	Yes	Age of the underlying data in seconds (0 = fetched live).
`x_payment_response`	No	Base64-encoded x402 settlement receipt (mirrors the X-PAYMENT-RESPONSE header). Only present when the call was paid with `x_payment`.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 15, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "Response for ``POST /arxiv-search``.",
+  "properties": {
+    "attribution": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Attribution"
+    },
+    "category": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Category"
+    },
+    "cost_usdc": {
+      "description": "Price charged in stablecoin units (USDC/USDT 1:1); 0 on the free tier.",
+      "title": "Cost Usdc",
+      "type": "number"
+    },
+    "fetched_at": {
+      "description": "UTC timestamp when the data was fetched.",
+      "format": "date-time",
+      "title": "Fetched At",
+      "type": "string"
+    },
+    "freshness_seconds": {
+      "description": "Age of the underlying data in seconds (0 = fetched live).",
+      "title": "Freshness Seconds",
+      "type": "integer"
+    },
+    "paper_count": {
+      "title": "Paper Count",
+      "type": "integer"
+    },
+    "papers": {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "title": "Papers",
+      "type": "array"
+    },
+    "query": {
+      "title": "Query",
+      "type": "string"
+    },
+    "routing": {
+      "description": "How the request was routed (provider, fallback, cache, latency).",
+      "properties": {
+        "cache_hit": {
+          "default": false,
+          "description": "True if the result was served from cache.",
+          "title": "Cache Hit",
+          "type": "boolean"
+        },
+        "fallback_used": {
+          "default": false,
+          "description": "True if the primary provider failed and a fallback served the result.",
+          "title": "Fallback Used",
+          "type": "boolean"
+        },
+        "latency_ms": {
+          "default": 0,
+          "description": "End-to-end routing latency in milliseconds.",
+          "title": "Latency Ms",
+          "type": "integer"
+        },
+        "provider": {
+          "description": "Name of the upstream provider that served the result.",
+          "title": "Provider",
+          "type": "string"
+        },
+        "providers_tried": {
+          "description": "Providers attempted, in order.",
+          "items": {
+            "type": "string"
+          },
+          "title": "Providers Tried",
+          "type": "array"
+        }
+      },
+      "required": [
+        "provider"
+      ],
+      "title": "RoutingMeta",
+      "type": "object"
+    },
+    "sort_by": {
+      "title": "Sort By",
+      "type": "string"
+    },
+    "source": {
+      "title": "Source",
+      "type": "string"
+    },
+    "token": {
+      "default": "USDC",
+      "description": "Token actually used for payment (USDC, USDT or FREE).",
+      "title": "Token",
+      "type": "string"
+    },
+    "total_results": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Total Results"
+    },
+    "x_payment_response": {
+      "description": "Base64-encoded x402 settlement receipt (mirrors the X-PAYMENT-RESPONSE header). Only present when the call was paid with `x_payment`.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "freshness_seconds",
+    "cost_usdc",
+    "routing",
+    "query",
+    "sort_by",
+    "papers",
+    "paper_count",
+    "source"
+  ],
+  "type": "object"
+}

AddedSep 13, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=true, signaling a safe, read-only operation. The description adds value by disclosing the payment model ('Pay per call with USDC or USDT on Base via x402. 3 free calls per wallet'), which is not covered by annotations. It does not mention rate limits or response size, but given the annotations, this is a minor gap.

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 concise and front-loads the core functionality ('Search arXiv preprints') followed by the return fields and options. The payment note is placed at the end, which is acceptable. Slightly more could be trimmed, but it is well-structured and efficient.

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?

The tool has an output schema (which presumably details return format) and 100% schema coverage, so the description need not explain return values. It covers the main purpose, payment, and optional filters. The description is complete enough for an agent to know how to call it, including the free tier and payment requirement, so the slight lack of rate limit info is not critical.

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?

The description mentions sorting and filtering by category, but the input schema already has detailed descriptions for all 7 parameters, covering the same information (e.g., query='Free-text search query', wallet='Unlocks the free tier'). The description adds a little context by noting the free tier for wallet, but it largely reiterates the schema. With 100% schema coverage, the baseline is 3, and the description does not significantly exceed it.

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 searches arXiv preprints and lists the specific returned fields (id, title, authors, abstract, categories, dates, PDF links), which is a specific verb+resource. It also mentions sorting and filtering options, making it easy to distinguish from sibling tools like 'news_search' or 'web_search' which serve different content types.

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?

The description explicitly states the tool is for searching arXiv preprints and mentions optional filtering by category and sorting. It does not explicitly contrast with siblings, but the specific domain (arXiv) and the detailed output fields give clear context on when to use it. The payment note also clarifies the usage context, though it is more about cost than selection.

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

All Agent Margin Router tools Inspect

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.