@mastra/mcp-docs-server 1.2.3-alpha.4 → 1.2.3-alpha.7
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/.docs/docs/observability/metrics/overview.md +2 -2
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/deepinfra.md +3 -2
- package/.docs/models/providers/friendli.md +1 -3
- package/.docs/models/providers/gmicloud.md +18 -15
- package/.docs/models/providers/inceptron.md +10 -8
- package/.docs/models/providers/llmgateway.md +2 -3
- package/.docs/models/providers/neuralwatt.md +9 -5
- package/.docs/reference/observability/metrics/automatic-metrics.md +2 -2
- package/CHANGELOG.md +14 -0
- package/package.json +5 -5
|
@@ -8,9 +8,9 @@ Three categories of metrics are emitted automatically:
|
|
|
8
8
|
- **Token usage metrics**: Input and output token counts broken down by type (text, cache, audio, image, reasoning).
|
|
9
9
|
- **Cost estimation**: Estimated cost per model call based on an embedded pricing registry.
|
|
10
10
|
|
|
11
|
-
> **Note:** Metrics require an
|
|
11
|
+
> **Note:** Metrics require an analytics-capable store for observability. Most relational databases (LibSQL, MSSQL) aren't supported for metrics. In-memory storage resets on restart.
|
|
12
12
|
>
|
|
13
|
-
> For local development, use [DuckDB](https://duckdb.org/) through `@mastra/duckdb`. For production, use [ClickHouse](https://clickhouse.com/) through `@mastra/clickhouse`.
|
|
13
|
+
> For local development, use [DuckDB](https://duckdb.org/) through `@mastra/duckdb`. For production, use [ClickHouse](https://clickhouse.com/) through `@mastra/clickhouse`. `PostgresStoreVNext` with the observability domain enabled also supports metrics, but always provide a time range to avoid full partition scans.
|
|
14
14
|
>
|
|
15
15
|
> Google Cloud Spanner supports metrics, but it's not recommended for heavy metrics workloads. The Spanner adapter disables metrics by default because metrics are write-heavy and scan-heavy. Set `disableMetrics: false` only for light workloads, or route metrics to an OLAP store.
|
|
16
16
|
|
package/.docs/models/index.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Model Providers
|
|
2
2
|
|
|
3
|
-
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to
|
|
3
|
+
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 4482 models from 134 providers through a single API.
|
|
4
4
|
|
|
5
5
|
## Features
|
|
6
6
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Deep Infra
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 26 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Deep Infra documentation](https://deepinfra.com/models).
|
|
6
6
|
|
|
@@ -57,6 +57,7 @@ for await (const chunk of stream) {
|
|
|
57
57
|
| `deepinfra/zai-org/GLM-4.7-Flash` | 203K | | | | | | $0.06 | $0.40 |
|
|
58
58
|
| `deepinfra/zai-org/GLM-5` | 203K | | | | | | $0.60 | $2 |
|
|
59
59
|
| `deepinfra/zai-org/GLM-5.1` | 203K | | | | | | $1 | $4 |
|
|
60
|
+
| `deepinfra/zai-org/GLM-5.2` | 1.0M | | | | | | $0.95 | $3 |
|
|
60
61
|
|
|
61
62
|
## Advanced configuration
|
|
62
63
|
|
|
@@ -85,7 +86,7 @@ const agent = new Agent({
|
|
|
85
86
|
model: ({ requestContext }) => {
|
|
86
87
|
const useAdvanced = requestContext.task === "complex";
|
|
87
88
|
return useAdvanced
|
|
88
|
-
? "deepinfra/zai-org/GLM-5.
|
|
89
|
+
? "deepinfra/zai-org/GLM-5.2"
|
|
89
90
|
: "deepinfra/MiniMaxAI/MiniMax-M2.5";
|
|
90
91
|
}
|
|
91
92
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Friendli
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 7 Friendli models through Mastra's model router. Authentication is handled automatically using the `FRIENDLI_TOKEN` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Friendli documentation](https://friendli.ai/docs/guides/serverless_endpoints/introduction).
|
|
6
6
|
|
|
@@ -36,8 +36,6 @@ for await (const chunk of stream) {
|
|
|
36
36
|
| --------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
37
|
| `friendli/deepseek-ai/DeepSeek-V3.2` | 164K | | | | | | $0.50 | $2 |
|
|
38
38
|
| `friendli/google/gemma-4-31B-it` | 262K | | | | | | $0.14 | $0.40 |
|
|
39
|
-
| `friendli/meta-llama/Llama-3.1-8B-Instruct` | 131K | | | | | | $0.10 | $0.10 |
|
|
40
|
-
| `friendli/meta-llama/Llama-3.3-70B-Instruct` | 131K | | | | | | $0.60 | $0.60 |
|
|
41
39
|
| `friendli/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.30 | $1 |
|
|
42
40
|
| `friendli/Qwen/Qwen3-235B-A22B-Instruct-2507` | 262K | | | | | | $0.20 | $0.80 |
|
|
43
41
|
| `friendli/zai-org/GLM-5` | 203K | | | | | | $1 | $3 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# GMI Cloud
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 11 GMI Cloud models through Mastra's model router. Authentication is handled automatically using the `GMICLOUD_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [GMI Cloud documentation](https://docs.gmicloud.ai).
|
|
6
6
|
|
|
@@ -15,7 +15,7 @@ const agent = new Agent({
|
|
|
15
15
|
id: "my-agent",
|
|
16
16
|
name: "My Agent",
|
|
17
17
|
instructions: "You are a helpful assistant",
|
|
18
|
-
model: "gmicloud/
|
|
18
|
+
model: "gmicloud/Qwen/Qwen3.7-Max"
|
|
19
19
|
});
|
|
20
20
|
|
|
21
21
|
// Generate a response
|
|
@@ -32,16 +32,19 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `gmicloud/anthropic/claude-opus-4.6`
|
|
38
|
-
| `gmicloud/anthropic/claude-opus-4.7`
|
|
39
|
-
| `gmicloud/anthropic/claude-sonnet-4.6`
|
|
40
|
-
| `gmicloud/deepseek-ai/DeepSeek-V4-Flash`
|
|
41
|
-
| `gmicloud/deepseek-ai/DeepSeek-V4-Pro`
|
|
42
|
-
| `gmicloud/moonshotai/Kimi-K2.6`
|
|
43
|
-
| `gmicloud/
|
|
44
|
-
| `gmicloud/
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ---------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `gmicloud/anthropic/claude-opus-4.6` | 410K | | | | | | $5 | $25 |
|
|
38
|
+
| `gmicloud/anthropic/claude-opus-4.7` | 410K | | | | | | $5 | $23 |
|
|
39
|
+
| `gmicloud/anthropic/claude-sonnet-4.6` | 410K | | | | | | $3 | $15 |
|
|
40
|
+
| `gmicloud/deepseek-ai/DeepSeek-V4-Flash` | 1.0M | | | | | | $0.11 | $0.22 |
|
|
41
|
+
| `gmicloud/deepseek-ai/DeepSeek-V4-Pro` | 1.0M | | | | | | $1 | $3 |
|
|
42
|
+
| `gmicloud/moonshotai/Kimi-K2.6` | 66K | | | | | | $0.85 | $4 |
|
|
43
|
+
| `gmicloud/moonshotai/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
|
|
44
|
+
| `gmicloud/Qwen/Qwen3.7-Max` | 1.0M | | | | | | $3 | $8 |
|
|
45
|
+
| `gmicloud/zai-org/GLM-5-FP8` | 203K | | | | | | $0.60 | $2 |
|
|
46
|
+
| `gmicloud/zai-org/GLM-5.1-FP8` | 203K | | | | | | $0.98 | $3 |
|
|
47
|
+
| `gmicloud/zai-org/GLM-5.2-FP8` | 1.0M | | | | | | $0.98 | $3 |
|
|
45
48
|
|
|
46
49
|
## Advanced configuration
|
|
47
50
|
|
|
@@ -53,7 +56,7 @@ const agent = new Agent({
|
|
|
53
56
|
name: "custom-agent",
|
|
54
57
|
model: {
|
|
55
58
|
url: "https://api.gmi-serving.com/v1",
|
|
56
|
-
id: "gmicloud/
|
|
59
|
+
id: "gmicloud/Qwen/Qwen3.7-Max",
|
|
57
60
|
apiKey: process.env.GMICLOUD_API_KEY,
|
|
58
61
|
headers: {
|
|
59
62
|
"X-Custom-Header": "value"
|
|
@@ -71,8 +74,8 @@ const agent = new Agent({
|
|
|
71
74
|
model: ({ requestContext }) => {
|
|
72
75
|
const useAdvanced = requestContext.task === "complex";
|
|
73
76
|
return useAdvanced
|
|
74
|
-
? "gmicloud/zai-org/GLM-5.
|
|
75
|
-
: "gmicloud/
|
|
77
|
+
? "gmicloud/zai-org/GLM-5.2-FP8"
|
|
78
|
+
: "gmicloud/Qwen/Qwen3.7-Max";
|
|
76
79
|
}
|
|
77
80
|
});
|
|
78
81
|
```
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Inceptron
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 6 Inceptron models through Mastra's model router. Authentication is handled automatically using the `INCEPTRON_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Inceptron documentation](https://docs.inceptron.io).
|
|
6
6
|
|
|
@@ -32,12 +32,14 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `inceptron/MiniMaxAI/MiniMax-M2.5`
|
|
38
|
-
| `inceptron/moonshotai/Kimi-K2.6`
|
|
39
|
-
| `inceptron/
|
|
40
|
-
| `inceptron/
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `inceptron/MiniMaxAI/MiniMax-M2.5` | 197K | | | | | | $0.15 | $0.90 |
|
|
38
|
+
| `inceptron/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.66 | $4 |
|
|
39
|
+
| `inceptron/moonshotai/Kimi-K2.6-Fast` | 262K | | | | | | $1 | $7 |
|
|
40
|
+
| `inceptron/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.75 | $4 |
|
|
41
|
+
| `inceptron/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
|
|
42
|
+
| `inceptron/zai-org/GLM-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
41
43
|
|
|
42
44
|
## Advanced configuration
|
|
43
45
|
|
|
@@ -67,7 +69,7 @@ const agent = new Agent({
|
|
|
67
69
|
model: ({ requestContext }) => {
|
|
68
70
|
const useAdvanced = requestContext.task === "complex";
|
|
69
71
|
return useAdvanced
|
|
70
|
-
? "inceptron/zai-org/GLM-5.
|
|
72
|
+
? "inceptron/zai-org/GLM-5.2"
|
|
71
73
|
: "inceptron/MiniMaxAI/MiniMax-M2.5";
|
|
72
74
|
}
|
|
73
75
|
});
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# LLM Gateway
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 180 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
|
|
6
6
|
|
|
@@ -127,9 +127,8 @@ for await (const chunk of stream) {
|
|
|
127
127
|
| `llmgateway/grok-build-0-1` | 256K | | | | | | $1 | $2 |
|
|
128
128
|
| `llmgateway/kimi-k2` | 256K | | | | | | $0.57 | $2 |
|
|
129
129
|
| `llmgateway/kimi-k2-thinking` | 262K | | | | | | $0.57 | $2 |
|
|
130
|
-
| `llmgateway/kimi-k2-thinking-turbo` | 262K | | | | | | $1 | $8 |
|
|
131
130
|
| `llmgateway/kimi-k2.5` | 262K | | | | | | $0.41 | $2 |
|
|
132
|
-
| `llmgateway/kimi-k2.6` | 262K | | | | | | $0.
|
|
131
|
+
| `llmgateway/kimi-k2.6` | 262K | | | | | | $0.40 | $2 |
|
|
133
132
|
| `llmgateway/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
134
133
|
| `llmgateway/kimi-k2.7-code-highspeed` | 262K | | | | | | $2 | $8 |
|
|
135
134
|
| `llmgateway/llama-3-70b-instruct` | 8K | | | | | | $0.51 | $0.74 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Neuralwatt
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 18 Neuralwatt models through Mastra's model router. Authentication is handled automatically using the `NEURALWATT_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Neuralwatt documentation](https://portal.neuralwatt.com/docs).
|
|
6
6
|
|
|
@@ -34,12 +34,17 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
36
|
| --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
-
| `neuralwatt/glm-5-fast` | 203K | | | | | | $1 | $4 |
|
|
38
|
-
| `neuralwatt/glm-5.1-fast` | 203K | | | | | | $1 | $4 |
|
|
39
37
|
| `neuralwatt/glm-5.2` | 1.0M | | | | | | $1 | $5 |
|
|
38
|
+
| `neuralwatt/glm-5.2-fast` | 1.0M | | | | | | $1 | $5 |
|
|
39
|
+
| `neuralwatt/glm-5.2-flex` | 1.0M | | | | | | $0.72 | $2 |
|
|
40
40
|
| `neuralwatt/glm-5.2-short` | 200K | | | | | | $1 | $5 |
|
|
41
|
+
| `neuralwatt/glm-5.2-short-fast` | 200K | | | | | | $1 | $5 |
|
|
42
|
+
| `neuralwatt/glm-5.2-short-fast-flex` | 200K | | | | | | $0.72 | $2 |
|
|
43
|
+
| `neuralwatt/glm-5.2-short-flex` | 200K | | | | | | $0.72 | $2 |
|
|
41
44
|
| `neuralwatt/kimi-k2.5-fast` | 262K | | | | | | $0.52 | $3 |
|
|
42
45
|
| `neuralwatt/kimi-k2.6-fast` | 262K | | | | | | $0.69 | $3 |
|
|
46
|
+
| `neuralwatt/kimi-k2.6-flex` | 262K | | | | | | $0.34 | $2 |
|
|
47
|
+
| `neuralwatt/kimi-k2.7-code-flex` | 262K | | | | | | $0.47 | $2 |
|
|
43
48
|
| `neuralwatt/moonshotai/Kimi-K2.5` | 262K | | | | | | $0.52 | $3 |
|
|
44
49
|
| `neuralwatt/moonshotai/Kimi-K2.6` | 262K | | | | | | $0.69 | $3 |
|
|
45
50
|
| `neuralwatt/moonshotai/Kimi-K2.7-Code` | 262K | | | | | | $0.95 | $4 |
|
|
@@ -47,7 +52,6 @@ for await (const chunk of stream) {
|
|
|
47
52
|
| `neuralwatt/Qwen/Qwen3.6-35B-A3B` | 131K | | | | | | $0.29 | $1 |
|
|
48
53
|
| `neuralwatt/qwen3.5-397b-fast` | 262K | | | | | | $0.69 | $4 |
|
|
49
54
|
| `neuralwatt/qwen3.6-35b-fast` | 131K | | | | | | $0.29 | $1 |
|
|
50
|
-
| `neuralwatt/zai-org/GLM-5.1-FP8` | 203K | | | | | | $1 | $4 |
|
|
51
55
|
|
|
52
56
|
## Advanced configuration
|
|
53
57
|
|
|
@@ -77,7 +81,7 @@ const agent = new Agent({
|
|
|
77
81
|
model: ({ requestContext }) => {
|
|
78
82
|
const useAdvanced = requestContext.task === "complex";
|
|
79
83
|
return useAdvanced
|
|
80
|
-
? "neuralwatt/
|
|
84
|
+
? "neuralwatt/qwen3.6-35b-fast"
|
|
81
85
|
: "neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8";
|
|
82
86
|
}
|
|
83
87
|
});
|
|
@@ -13,7 +13,7 @@ Metrics are extracted from spans when they end. The observability layer inspects
|
|
|
13
13
|
Two conditions must be true for a metric to reach storage:
|
|
14
14
|
|
|
15
15
|
1. `MastraStorageExporter` is configured as an exporter.
|
|
16
|
-
2. The storage backend supports metrics (ClickHouse or
|
|
16
|
+
2. The storage backend supports metrics (ClickHouse, DuckDB, or Postgres v-next with the observability domain enabled).
|
|
17
17
|
|
|
18
18
|
If metrics aren't available, see [troubleshooting](#troubleshooting).
|
|
19
19
|
|
|
@@ -116,7 +116,7 @@ When you spot a spike in latency or token usage on the Metrics dashboard, correl
|
|
|
116
116
|
|
|
117
117
|
- **Observability is configured**: Verify that your `Mastra` instance has an `observability` config with at least one exporter.
|
|
118
118
|
- **`MastraStorageExporter` or `MastraPlatformExporter` is present**: Other exporters (Datadog, Langfuse, etc.) don't surface metrics in Mastra. `MastraStorageExporter` is required for the local Studio dashboard, and `MastraPlatformExporter` is required to view metrics in Mastra platform.
|
|
119
|
-
- **Storage supports metrics**: Metrics require an
|
|
119
|
+
- **Storage supports metrics**: Metrics require an analytics-capable store (ClickHouse, DuckDB, or Postgres v-next with the observability domain enabled). Other row-oriented databases (LibSQL, MSSQL) and document stores (MongoDB) aren't supported for metrics.
|
|
120
120
|
- **Sampling isn't 0%**: If sampling probability is `0` or strategy is `never`, all spans become no-ops and no metrics are extracted.
|
|
121
121
|
|
|
122
122
|
### Duration metrics are missing
|
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,19 @@
|
|
|
1
1
|
# @mastra/mcp-docs-server
|
|
2
2
|
|
|
3
|
+
## 1.2.3-alpha.7
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- Updated dependencies [[`cdd5f93`](https://github.com/mastra-ai/mastra/commit/cdd5f939cefa67390629704dce92563ccbf492b2), [`1b8728a`](https://github.com/mastra-ai/mastra/commit/1b8728a57fd844205a452b0b4216d20ff60c784a), [`213feb8`](https://github.com/mastra-ai/mastra/commit/213feb87bfdd1d8ec00ea660e218f9bcfcb34e7b)]:
|
|
8
|
+
- @mastra/core@1.48.0-alpha.3
|
|
9
|
+
|
|
10
|
+
## 1.2.3-alpha.5
|
|
11
|
+
|
|
12
|
+
### Patch Changes
|
|
13
|
+
|
|
14
|
+
- Updated dependencies [[`e420b3c`](https://github.com/mastra-ai/mastra/commit/e420b3c3ffc98bbc5b791897ea390bb47af99696)]:
|
|
15
|
+
- @mastra/core@1.48.0-alpha.2
|
|
16
|
+
|
|
3
17
|
## 1.2.3-alpha.2
|
|
4
18
|
|
|
5
19
|
### Patch Changes
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mastra/mcp-docs-server",
|
|
3
|
-
"version": "1.2.3-alpha.
|
|
3
|
+
"version": "1.2.3-alpha.7",
|
|
4
4
|
"description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -28,8 +28,8 @@
|
|
|
28
28
|
"jsdom": "^26.1.0",
|
|
29
29
|
"local-pkg": "^1.1.2",
|
|
30
30
|
"zod": "^4.4.3",
|
|
31
|
-
"@mastra/
|
|
32
|
-
"@mastra/
|
|
31
|
+
"@mastra/mcp": "^1.12.0",
|
|
32
|
+
"@mastra/core": "1.48.0-alpha.3"
|
|
33
33
|
},
|
|
34
34
|
"devDependencies": {
|
|
35
35
|
"@hono/node-server": "^1.19.11",
|
|
@@ -45,9 +45,9 @@
|
|
|
45
45
|
"tsx": "^4.22.4",
|
|
46
46
|
"typescript": "^6.0.3",
|
|
47
47
|
"vitest": "4.1.8",
|
|
48
|
-
"@internal/lint": "0.0.109",
|
|
49
48
|
"@internal/types-builder": "0.0.84",
|
|
50
|
-
"@mastra/core": "1.48.0-alpha.
|
|
49
|
+
"@mastra/core": "1.48.0-alpha.3",
|
|
50
|
+
"@internal/lint": "0.0.109"
|
|
51
51
|
},
|
|
52
52
|
"homepage": "https://mastra.ai",
|
|
53
53
|
"repository": {
|