Paperswithcode

Get Repositories

get_repositories

Read-onlyIdempotent

Find IMPLEMENTATIONS of a paper (by arXiv id): the linked GitHub repository plus the most popular Hugging Face models, demo Spaces, and datasets that implement or reproduce it — the "papers with code" view. Use for "code/implementation for ", "models trained on ".

Input Schema

Name	Required	Description	Default
`arxiv_id`	Yes	arXiv identifier (e.g. "2312.00752").

Output Schema

Name	Required	Description	Default
`title`	No
`counts`	No
`arxiv_id`	No
`datasets`	No
`top_models`	No
`demo_spaces`	No
`github_repo`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedNov 3, 2026

addedOutput schema / properties / arxiv_id
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / counts

Added value: +{
+  "properties": {
+    "datasets": {
+      "type": "number"
+    },
+    "models": {
+      "type": "number"
+    },
+    "spaces": {
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / datasets

Added value: +{
+  "items": {
+    "properties": {
+      "downloads": {
+        "type": "number"
+      },
+      "id": {
+        "type": "string"
+      },
+      "url": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / demo_spaces

Added value: +{
+  "items": {
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "likes": {
+        "type": "null"
+      },
+      "url": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / github_repo
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / paper_id

Removed value: -{
-  "description": "The paper ID queried",
-  "type": "string"
-}

removedOutput schema / properties / repositories

Removed value: -{
-  "description": "Array of repository objects",
-  "items": {
-    "properties": {
-      "description": {
-        "description": "Repository description",
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "framework": {
-        "description": "Framework used in the repository",
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "id": {
-        "description": "Repository ID",
-        "type": [
-          "number",
-          "null"
-        ]
-      },
-      "is_official": {
-        "description": "Whether this is the official implementation",
-        "type": [
-          "boolean",
-          "null"
-        ]
-      },
-      "name": {
-        "description": "Repository name",
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "owner": {
-        "description": "Repository owner",
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "stars": {
-        "description": "Number of stars on the repository",
-        "type": [
-          "number",
-          "null"
-        ]
-      },
-      "url": {
-        "description": "Repository URL",
-        "type": [
-          "string",
-          "null"
-        ]
-      }
-    },
-    "required": [
-      "id",
-      "url",
-      "owner",
-      "name",
-      "description",
-      "stars",
-      "framework",
-      "is_official"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

addedOutput schema / properties / title
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / top_models

Added value: +{
+  "items": {
+    "properties": {
+      "downloads": {
+        "type": "number"
+      },
+      "id": {
+        "type": "string"
+      },
+      "likes": {
+        "type": "number"
+      },
+      "task": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "url": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

removedOutput schema / properties / total

Removed value: -{
-  "description": "Total number of repositories linked to the paper",
-  "type": "number"
-}

removedOutput schema / required

Removed value: -[
-  "paper_id",
-  "total",
-  "repositories"
-]

Changed1 schema field changedJul 29, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "id": "attention-is-all-you-need"
-  }
-]New value: +[
+  {
+    "arxiv_id": "2312.00752"
+  }
+]

Changed3 schema fields changedJun 25, 2026

addedInput schema / properties / arxiv_id

Added value: +{
+  "description": "arXiv identifier (e.g. \"2312.00752\").",
+  "type": "string"
+}

removedInput schema / properties / id

Removed value: -{
-  "description": "Papers With Code paper ID",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "id"
-]New value: +[
+  "arxiv_id"
+]

Changed1 schema field changedMay 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "paper_id": {
+      "description": "The paper ID queried",
+      "type": "string"
+    },
+    "repositories": {
+      "description": "Array of repository objects",
+      "items": {
+        "properties": {
+          "description": {
+            "description": "Repository description",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "framework": {
+            "description": "Framework used in the repository",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "id": {
+            "description": "Repository ID",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "is_official": {
+            "description": "Whether this is the official implementation",
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "name": {
+            "description": "Repository name",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "owner": {
+            "description": "Repository owner",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "stars": {
+            "description": "Number of stars on the repository",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "url": {
+            "description": "Repository URL",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "url",
+          "owner",
+          "name",
+          "description",
+          "stars",
+          "framework",
+          "is_official"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "description": "Total number of repositories linked to the paper",
+      "type": "number"
+    }
+  },
+  "required": [
+    "paper_id",
+    "total",
+    "repositories"
+  ],
+  "type": "object"
+}

Changed1 schema field changedMay 6, 2026

addedInput schema / examples

Added value: +[
+  {
+    "id": "attention-is-all-you-need"
+  }
+]

First observedApr 22, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, open-world, non-destructive behavior. The description adds valuable context by specifying exactly what is returned (GitHub repo plus most popular HF models, Spaces, datasets), which goes beyond the safety profile. No rate-limit or auth notes, but those are less critical here.

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

Conciseness5/5

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

Two sentences, front-loaded with the core action and output, followed by concrete usage triggers. No filler; every clause adds information.

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?

With a rich output schema covering return values, complete annotations, and full parameter documentation, the description only needs to convey purpose and selection guidance — which it does fully by naming the output contents and use cases.

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 coverage is 100% for the single arxiv_id parameter and includes an example, so the schema carries the parameter documentation. The description only implies the parameter through '(by arXiv id)' and adds no syntax or format detail beyond the schema.

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 ('Find') and resource ('IMPLEMENTATIONS of a paper'), and names the exact output contents (GitHub repo, Hugging Face models, Spaces, datasets). The 'papers with code view' framing makes it immediately distinguishable from get_paper or search_papers siblings.

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

Usage Guidelines4/5

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

Provides explicit trigger phrases ('code/implementation for <paper>', 'models trained on <paper>') that tell the agent when to select this tool. It stops short of naming an alternative tool or stating when-not-to-use, so it falls just below full marks.

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

All Paperswithcode 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.