pokerdata-mcp 1.0.1 → 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 +19 -5
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -85,7 +85,9 @@ curl -s https://pokerdata.io/api/mcp -H 'Content-Type: application/json' \
|
|
|
85
85
|
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_node","arguments":{"game":"nl","stack":100,"history":"UTG"}}}'
|
|
86
86
|
```
|
|
87
87
|
|
|
88
|
-
More in [`examples/`](examples/):
|
|
88
|
+
More in [`examples/`](examples/): a live example for every MCP tool,
|
|
89
|
+
real-world scenarios (NL and PLO ranges, the npm bridge, raw JSON-RPC, Node,
|
|
90
|
+
Python, client configs, REST) and a smoke test, all with captured responses.
|
|
89
91
|
|
|
90
92
|
## Tools
|
|
91
93
|
|
|
@@ -103,6 +105,11 @@ Preflop spots are action paths such as `UTG_60%_HJ_Call` (NLHE) or
|
|
|
103
105
|
default; pass `detail: "full"` for complete maps. Full contract:
|
|
104
106
|
[docs.pokerdata.io/ranges](https://docs.pokerdata.io/ranges).
|
|
105
107
|
|
|
108
|
+
Every tool's full definition — name, title, description, input schema, output
|
|
109
|
+
schema and behaviour annotations — exactly as the server returns it from
|
|
110
|
+
`tools/list`, is in [`tools.json`](tools.json). Every tool also returns
|
|
111
|
+
`structuredContent` matching its output schema alongside the text result.
|
|
112
|
+
|
|
106
113
|
## Plans
|
|
107
114
|
|
|
108
115
|
| Plan | Price | What you get |
|
|
@@ -126,10 +133,17 @@ before connecting anything:
|
|
|
126
133
|
|
|
127
134
|
## How the solves were made
|
|
128
135
|
|
|
129
|
-
Preflop cash trees
|
|
130
|
-
solves come from our own engine, validated against
|
|
131
|
-
|
|
132
|
-
|
|
136
|
+
Preflop cash trees come from established commercial solver packs. The
|
|
137
|
+
tournament and postflop solves come from our own engine, validated against an
|
|
138
|
+
independent reference solve of the same game tree — the comparison, position
|
|
139
|
+
by position, is at
|
|
140
|
+
[pokerdata.io/methodology](https://pokerdata.io/methodology).
|
|
141
|
+
|
|
142
|
+
Nothing is estimated to fill a gap. Postflop exploitability is published per
|
|
143
|
+
board (`list_postflop_packs` with a `pack`) and omitted where the solve does
|
|
144
|
+
not carry it. No preflop dataset publishes exploitability, convergence or
|
|
145
|
+
iteration counts, and `get_exploitability` says so instead of returning a
|
|
146
|
+
number.
|
|
133
147
|
|
|
134
148
|
## Related
|
|
135
149
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "pokerdata-mcp",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.2",
|
|
4
4
|
"description": "MCP server for GTO poker solver data: preflop ranges and postflop strategy for no-limit hold'em and pot-limit Omaha, from pokerdata.io.",
|
|
5
5
|
"mcpName": "io.github.hft-studio/pokerdata",
|
|
6
6
|
"bin": {
|