Koskamo

iconlab MCP

An MCP server for searching a corpus of over 324k icons or generating new ones in the Lucide grammar. It supports instant search, retrieving icons in various formats, and a grammar-locked generation loop for creating custom icons when existing ones do not fit.

Visit op0ai

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

iconlab MCP logo, by op0aiCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by op0ai
You need:Anonymous: 5 generations/day (search unlimited). Free account: 25/mo + saved collections + custom registries.
MCP endpoint (Streamable HTTP)
https://iconlab.skillkit.run/mcp
Vendor documentation

What its tools do

3 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (3)

3 of 3 have a description · 0 of 3 declare behavior hints · 2 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search for icons across curated and breadth sets
  • Retrieve icons in SVG, JSX, or motion formats
  • Generate new icons in the Lucide dialect

Source and maintenance

Community listingRegistry 0.2.1
mcp-registry: io.github.op0ai/iconlab@0.2.1Project website

Protocol and capabilities

Server
iconlab 0.2.0
MCP protocol negotiated in check
2025-11-25
Tools
3 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Tools

3 advertised

search_icons
Advertised by the server during the last successful anonymous check.

Search the iconlab corpus (Lucide static + lucide-animated variants) by concept. Returns scored matches with slugs, sources and licenses.

search_icons input schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "number",
      "description": "max results, 1-50 (default 12)"
    },
    "query": {
      "type": "string",
      "description": "concept, e.g. 'drum' or 'vector database'"
    }
  }
}
search_icons output schema
{
  "type": "object",
  "required": [
    "query",
    "total",
    "truncated",
    "results"
  ],
  "properties": {
    "query": {
      "type": "string"
    },
    "total": {
      "type": "number",
      "description": "matches found (counting stops at limit+1, so total may read limit+1 when truncated)"
    },
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "slug",
          "score",
          "source",
          "license",
          "animatedVariant"
        ],
        "properties": {
          "slug": {
            "type": "string"
          },
          "score": {
            "type": "number",
            "description": "relevance, 0-1"
          },
          "source": {
            "type": "string",
            "description": "lucide | lucide-animated"
          },
          "license": {
            "type": "string",
            "description": "SPDX id of the source set"
          },
          "animatedVariant": {
            "type": "boolean",
            "description": "an animated variant exists for this slug"
          }
        }
      }
    },
    "truncated": {
      "type": "boolean",
      "description": "true when more matches exist beyond `results`"
    }
  }
}
get_icon
Advertised by the server during the last successful anonymous check.

Fetch one icon by slug. format='svg' (default) returns the SVG document; 'jsx' returns a lucide-react-compatible TSX component; 'motion' returns a TSX component with a stroke-draw entrance.

get_icon input schema
{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string"
    },
    "format": {
      "enum": [
        "svg",
        "jsx",
        "motion"
      ],
      "type": "string"
    }
  }
}
get_icon output schema
{
  "oneOf": [
    {
      "type": "object",
      "required": [
        "slug",
        "format",
        "source",
        "license",
        "content"
      ],
      "properties": {
        "slug": {
          "type": "string"
        },
        "format": {
          "enum": [
            "svg",
            "jsx",
            "motion"
          ],
          "type": "string"
        },
        "source": {
          "type": "string"
        },
        "content": {
          "type": "string",
          "description": "SVG document (format=svg) or TSX component source (jsx/motion)"
        },
        "license": {
          "type": "string"
        }
      }
    },
    {
      "type": "object",
      "required": [
        "error"
      ],
      "properties": {
        "error": {
          "type": "object",
          "required": [
            "code",
            "message"
          ],
          "properties": {
            "code": {
              "enum": [
                "unknown_icon"
              ],
              "type": "string"
            },
            "quota": {
              "type": "object",
              "description": "present on quota_exceeded: { used, limit, tier }"
            },
            "message": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}
generate_icon
Advertised by the server during the last successful anonymous check.

Generate a NEW icon in the Lucide grammar for a concept that doesn't exist yet. Grab-first: returns mode='grab' with matches when a strong existing icon covers the prompt. Otherwise runs the lint + critique + repair loop and returns lint-scored candidates. Subject to quota (errors carry error.code='quota_exceeded').

generate_icon input schema
{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "the concept, e.g. 'portafilter'"
    }
  }
}
generate_icon output schema
{
  "oneOf": [
    {
      "type": "object",
      "required": [
        "mode",
        "matches"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "generation record id (mode=generated); bench at /gen/{id}, record kept 90 days"
        },
        "ms": {
          "type": "number"
        },
        "mode": {
          "enum": [
            "grab",
            "generated"
          ],
          "type": "string",
          "description": "grab = strong existing matches, no generation ran"
        },
        "quota": {
          "type": "object",
          "description": "{ used, limit } after this call"
        },
        "prompt": {
          "type": "string"
        },
        "reason": {
          "type": "string"
        },
        "matches": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "slug",
              "score",
              "source",
              "license"
            ],
            "properties": {
              "slug": {
                "type": "string"
              },
              "score": {
                "type": "number"
              },
              "source": {
                "type": "string"
              },
              "license": {
                "type": "string"
              }
            }
          }
        },
        "createdAt": {
          "type": "string"
        },
        "candidates": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "name",
              "body",
              "score",
              "pass",
              "rounds"
            ],
            "properties": {
              "body": {
                "type": "string",
                "description": "inner SVG body in the 24x24 Lucide grammar (stroke-2, no fills)"
              },
              "name": {
                "type": "string"
              },
              "pass": {
                "type": "boolean"
              },
              "score": {
                "type": "number",
                "description": "grammar lint score, 0-100"
              },
              "rounds": {
                "type": "number",
                "description": "repair rounds used"
              },
              "violations": {
                "type": "array",
                "items": {
                  "type": "object"
                }
              },
              "visionNote": {
                "type": "string"
              },
              "visionVerdict": {
                "type": "string"
              }
            }
          }
        },
        "modelCalls": {
          "type": "number"
        },
        "provenance": {
          "type": "object",
          "description": "{ attribution, license: 'yours', source: 'generated' }"
        }
      }
    },
    {
      "type": "object",
      "required": [
        "error"
      ],
      "properties": {
        "error": {
          "type": "object",
          "required": [
            "code",
            "message"
          ],
          "properties": {
            "code": {
              "enum": [
                "prompt_too_short",
                "quota_exceeded",
                "internal"
              ],
              "type": "string"
            },
            "quota": {
              "type": "object",
              "description": "present on quota_exceeded: { used, limit, tier }"
            },
            "message": {
              "type": "string"
            }
          }
        }
      }
    }
  ]
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
287 ms
95th percentile latency
287 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 287 ms · metadata changed · 3 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http iconlab-mcp https://iconlab.skillkit.run/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add iconlab-mcp --url https://iconlab.skillkit.run/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable iconlab-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "iconlab-mcp": {
      "url": "https://iconlab.skillkit.run/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "iconlab-mcp": {
      "type": "streamableHttp",
      "url": "https://iconlab.skillkit.run/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start iconlab-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "iconlab-mcp": {
      "type": "http",
      "url": "https://iconlab.skillkit.run/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http iconlab-mcp https://iconlab.skillkit.run/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://iconlab.skillkit.run/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "iconlab-mcp": {
      "serverUrl": "https://iconlab.skillkit.run/mcp"
    }
  }
}

Let your agent find its tools

Find servers like iconlab MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 633