@konseki/mcp 1.0.0 → 1.0.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -2,13 +2,19 @@
2
2
 
3
3
  Official Model Context Protocol server for Konseki.
4
4
 
5
+ Konseki is a pre-computed historical market context API for global equities, built for AI trading and quants. It matches current market conditions against historical analogs and returns structured pattern-match data, outcome distributions, and match-quality scores, grounding an AI agent's reasoning in evidence rather than generic commentary.
6
+
5
7
  Konseki MCP is a direct wrapper around the Konseki public API. It lets AI agents and AI trading tools call Konseki endpoints through MCP tools while preserving the raw API response JSON for the user or downstream application to interpret.
6
8
 
9
+ Published package: [`@konseki/mcp`](https://www.npmjs.com/package/@konseki/mcp)
10
+
7
11
  ## Requirements
8
12
 
9
13
  - Node.js 20 or newer.
10
14
  - A Konseki API key.
11
15
 
16
+ Get an API key from [konseki.io](https://konseki.io).
17
+
12
18
  ## Design Principles
13
19
 
14
20
  - Direct API wrapper: the MCP server fetches Konseki API responses and returns them without interpretation.
@@ -79,7 +85,7 @@ The server requests gzip-compressed API responses and decompresses them locally
79
85
 
80
86
  ## Installation
81
87
 
82
- Use the package through an MCP client with `npx`:
88
+ Use the published npm package through an MCP client with `npx`:
83
89
 
84
90
  ```json
85
91
  {
@@ -95,7 +101,16 @@ Use the package through an MCP client with `npx`:
95
101
  }
96
102
  ```
97
103
 
98
- For local development from this checkout, configure your MCP client to run the built server:
104
+ This is the recommended configuration for users who want the official released package from npm.
105
+
106
+ ## Local Development
107
+
108
+ For development from this checkout, install dependencies, build the package, and configure your MCP client to run the built server:
109
+
110
+ ```sh
111
+ npm install
112
+ npm run build
113
+ ```
99
114
 
100
115
  ```json
101
116
  {
package/dist/server.js CHANGED
@@ -3,7 +3,7 @@ import { analysisInputSchema, createAnalysisToolHandler, createMetadataToolHandl
3
3
  export function createKonsekiMcpServer(client) {
4
4
  const server = new McpServer({
5
5
  name: "konseki-mcp",
6
- version: "1.0.0",
6
+ version: "1.0.2",
7
7
  });
8
8
  server.registerTool("get_konseki_metadata", {
9
9
  description: "Fetch raw metadata JSON from the Konseki public API.",
package/package.json CHANGED
@@ -1,9 +1,17 @@
1
1
  {
2
2
  "name": "@konseki/mcp",
3
- "version": "1.0.0",
3
+ "version": "1.0.2",
4
4
  "description": "Official Konseki MCP server: a direct AI-agent wrapper around the Konseki public API for historical market context.",
5
5
  "private": false,
6
6
  "type": "module",
7
+ "repository": {
8
+ "type": "git",
9
+ "url": "https://github.com/konseki-io/konseki-mcp.git"
10
+ },
11
+ "homepage": "https://konseki.io",
12
+ "bugs": {
13
+ "url": "https://github.com/konseki-io/konseki-mcp/issues"
14
+ },
7
15
  "bin": {
8
16
  "konseki-mcp": "dist/index.js"
9
17
  },