@mastra/mcp-docs-server 1.2.13-alpha.1 → 1.2.13-alpha.4

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.
Files changed (15) hide show
  1. package/.docs/models/environment-variables.md +1 -1
  2. package/.docs/models/gateways/vercel.md +2 -1
  3. package/.docs/models/index.md +1 -1
  4. package/.docs/models/providers/crof.md +2 -1
  5. package/.docs/models/providers/empiriolabs.md +2 -1
  6. package/.docs/models/providers/huggingface.md +3 -1
  7. package/.docs/models/providers/hyper.md +8 -6
  8. package/.docs/models/providers/llmgateway.md +1 -1
  9. package/.docs/models/providers/neuralwatt.md +3 -1
  10. package/.docs/models/providers/scaleway.md +1 -3
  11. package/.docs/models/providers/the-grid-ai.md +3 -3
  12. package/.docs/reference/cli/mastra.md +5 -1
  13. package/.docs/reference/processors/processor-interface.md +14 -2
  14. package/CHANGELOG.md +14 -0
  15. package/package.json +3 -3
package/.docs/models/environment-variables.md CHANGED
@@ -139,7 +139,7 @@ List of required environment variables for each model provider and gateway suppo
139
139
  | [Tencent Coding Plan (China)](https://mastra.ai/models/providers/tencent-coding-plan) | `tencent-coding-plan/*` | `TENCENT_CODING_PLAN_API_KEY` |
140
140
  | [Tencent Token Plan](https://mastra.ai/models/providers/tencent-token-plan) | `tencent-token-plan/*` | `TENCENT_TOKEN_PLAN_API_KEY` |
141
141
  | [Tencent TokenHub](https://mastra.ai/models/providers/tencent-tokenhub) | `tencent-tokenhub/*` | `TENCENT_TOKENHUB_API_KEY` |
142
- | [The Grid AI](https://mastra.ai/models/providers/the-grid-ai) | `the-grid-ai/*` | `THEGRIDAI_API_KEY` |
142
+ | [The Grid AI](https://mastra.ai/models/providers/the-grid-ai) | `the-grid-ai/*` | `THEGRID_API_KEY` |
143
143
  | [Thinking Machines](https://mastra.ai/models/providers/thinkingmachines) | `thinkingmachines/*` | `TINKER_API_KEY` |
144
144
  | [Tinfoil](https://mastra.ai/models/providers/tinfoil) | `tinfoil/*` | `TINFOIL_API_KEY` |
145
145
  | [Together AI](https://mastra.ai/models/providers/togetherai) | `togetherai/*` | `TOGETHER_API_KEY` |
package/.docs/models/gateways/vercel.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Vercel logo](https://models.dev/logos/vercel.svg)Vercel
4
4
 
5
- Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 307 models through Mastra's model router.
5
+ Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 308 models through Mastra's model router.
6
6
 
7
7
  Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
8
8
 
@@ -326,6 +326,7 @@ ANTHROPIC_API_KEY=ant-...
326
326
  | `xai/grok-stt` |
327
327
  | `xai/grok-tts` |
328
328
  | `xai/grok-voice-think-fast-1.0` |
329
+ | `xai/grok-voice-think-fast-2.0` |
329
330
  | `xiaomi/mimo-v2.5` |
330
331
  | `xiaomi/mimo-v2.5-pro` |
331
332
  | `zai/glm-4.5` |
package/.docs/models/index.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # Model Providers
4
4
 
5
- Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 5145 models from 164 providers through a single API.
5
+ Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 5151 models from 164 providers through a single API.
6
6
 
7
7
  ## Features
8
8
 
package/.docs/models/providers/crof.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![CrofAI logo](https://models.dev/logos/crof.svg)CrofAI
4
4
 
5
- Access 24 CrofAI models through Mastra's model router. Authentication is handled automatically using the `CROF_API_KEY` environment variable.
5
+ Access 25 CrofAI models through Mastra's model router. Authentication is handled automatically using the `CROF_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [CrofAI documentation](https://crof.ai/docs).
8
8
 
@@ -55,6 +55,7 @@ for await (const chunk of stream) {
55
55
  | `crof/kimi-k2.6` | 262K | | | | | | $0.50 | $2 |
56
56
  | `crof/kimi-k2.7-code` | 262K | | | | | | $0.55 | $2 |
57
57
  | `crof/kimi-k3` | 1.0M | | | | | | $2 | $8 |
58
+ | `crof/kimi-k3-eco` | 1.0M | | | | | | $1 | $4 |
58
59
  | `crof/mimo-v2.5-pro` | 1.0M | | | | | | $0.40 | $0.80 |
59
60
  | `crof/minimax-m2.5` | 205K | | | | | | $0.11 | $0.95 |
60
61
  | `crof/qwen3.5-397b-a17b` | 262K | | | | | | $0.35 | $2 |
package/.docs/models/providers/empiriolabs.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![EmpirioLabs AI logo](https://models.dev/logos/empiriolabs.svg)EmpirioLabs AI
4
4
 
5
- Access 36 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
5
+ Access 37 EmpirioLabs AI models through Mastra's model router. Authentication is handled automatically using the `EMPIRIOLABS_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [EmpirioLabs AI documentation](https://docs.empiriolabs.ai).
8
8
 
@@ -63,6 +63,7 @@ for await (const chunk of stream) {
63
63
  | `empiriolabs/qwen3-5-9b` | 262K | | | | | | $0.09 | $0.13 |
64
64
  | `empiriolabs/qwen3-5-plus` | 1.0M | | | | | | $0.36 | $2 |
65
65
  | `empiriolabs/qwen3-6-27b` | 256K | | | | | | $0.41 | $2 |
66
+ | `empiriolabs/qwen3-6-35b-a3b` | 131K | | | | | | $0.07 | $0.42 |
66
67
  | `empiriolabs/qwen3-6-flash` | 1.0M | | | | | | $0.25 | $2 |
67
68
  | `empiriolabs/qwen3-6-max-preview` | 256K | | | | | | $1 | $8 |
68
69
  | `empiriolabs/qwen3-6-plus` | 1.0M | | | | | | $0.50 | $3 |
package/.docs/models/providers/huggingface.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Hugging Face logo](https://models.dev/logos/huggingface.svg)Hugging Face
4
4
 
5
- Access 53 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
5
+ Access 55 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
6
6
 
7
7
  Learn more in the [Hugging Face documentation](https://huggingface.co).
8
8
 
@@ -77,6 +77,8 @@ for await (const chunk of stream) {
77
77
  | `huggingface/Qwen/Qwen3.6-35B-A3B` | 262K | | | | | | $0.15 | $0.95 |
78
78
  | `huggingface/stepfun-ai/Step-3.5-Flash` | 262K | | | | | | $0.10 | $0.30 |
79
79
  | `huggingface/stepfun-ai/Step-3.7-Flash` | 262K | | | | | | $0.20 | $1 |
80
+ | `huggingface/tencent/Hy3` | 262K | | | | | | $0.14 | $0.58 |
81
+ | `huggingface/thinkingmachines/Inkling` | 1.0M | | | | | | $1 | $4 |
80
82
  | `huggingface/XiaomiMiMo/MiMo-V2-Flash` | 262K | | | | | | $0.10 | $0.30 |
81
83
  | `huggingface/XiaomiMiMo/MiMo-V2.5` | 262K | | | | | | $0.40 | $2 |
82
84
  | `huggingface/XiaomiMiMo/MiMo-V2.5-Pro` | 1.0M | | | | | | $1 | $3 |
package/.docs/models/providers/hyper.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Charm Hyper logo](https://models.dev/logos/hyper.svg)Charm Hyper
4
4
 
5
- Access 20 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
5
+ Access 22 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Charm Hyper documentation](https://hyper.charm.land).
8
8
 
@@ -38,22 +38,24 @@ for await (const chunk of stream) {
38
38
  | ---------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
39
  | `hyper/deepseek-v4-flash` | 1.0M | | | | | | $0.20 | $0.40 |
40
40
  | `hyper/deepseek-v4-pro` | 1.0M | | | | | | $2 | $5 |
41
- | `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.12 | $0.41 |
42
- | `hyper/glm-5` | 203K | | | | | | $0.81 | $3 |
41
+ | `hyper/gemma-4-26b-a4b-it` | 256K | | | | | | $0.12 | $0.42 |
42
+ | `hyper/glm-5` | 203K | | | | | | $0.88 | $3 |
43
43
  | `hyper/glm-5.1` | 203K | | | | | | $2 | $5 |
44
44
  | `hyper/glm-5.2` | 1.0M | | | | | | $1 | $4 |
45
- | `hyper/gpt-oss-120b` | 131K | | | | | | $0.18 | $0.68 |
45
+ | `hyper/gpt-oss-120b` | 131K | | | | | | $0.18 | $0.61 |
46
46
  | `hyper/kimi-k2.5` | 262K | | | | | | $0.53 | $3 |
47
47
  | `hyper/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
48
48
  | `hyper/kimi-k2.7-code` | 256K | | | | | | $0.95 | $4 |
49
- | `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.61 | $1 |
49
+ | `hyper/kimi-k3` | 1.0M | | | | | | $3 | $16 |
50
+ | `hyper/llama-3.3-70b-instruct` | 128K | | | | | | $0.51 | $1 |
50
51
  | `hyper/llama-4-maverick-17b-128e-instruct-fp8` | 430K | | | | | | $0.28 | $0.93 |
51
- | `hyper/minimax-m2.7` | 205K | | | | | | $0.41 | $2 |
52
+ | `hyper/minimax-m2.7` | 205K | | | | | | $0.48 | $2 |
52
53
  | `hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar` | 106K | | | | | | $0.57 | $2 |
53
54
  | `hyper/qwen3-next-80b-a3b-instruct` | 262K | | | | | | $0.12 | $1 |
54
55
  | `hyper/qwen3.6-flash` | 1.0M | | | | | | $1 | $4 |
55
56
  | `hyper/qwen3.6-max` | 256K | | | | | | $2 | $12 |
56
57
  | `hyper/qwen3.6-plus` | 1.0M | | | | | | $2 | $6 |
58
+ | `hyper/qwen3.7-flash` | 1.0M | | | | | | $0.20 | $0.80 |
57
59
  | `hyper/qwen3.7-max` | 1.0M | | | | | | $3 | $8 |
58
60
  | `hyper/qwen3.7-plus` | 1.0M | | | | | | $1 | $5 |
59
61
 
package/.docs/models/providers/llmgateway.md CHANGED
@@ -207,7 +207,7 @@ for await (const chunk of stream) {
207
207
  | `llmgateway/qwen3-vl-plus` | 262K | | | | | | $0.20 | $2 |
208
208
  | `llmgateway/qwen3.5-9b` | 262K | | | | | | $0.10 | $0.15 |
209
209
  | `llmgateway/qwen3.6-35b-a3b` | 262K | | | | | | $0.25 | $1 |
210
- | `llmgateway/qwen3.6-flash` | 262K | | | | | | $0.15 | $0.90 |
210
+ | `llmgateway/qwen3.6-flash` | 1.0M | | | | | | $0.25 | $2 |
211
211
  | `llmgateway/qwen3.6-max-preview` | 262K | | | | | | $1 | $8 |
212
212
  | `llmgateway/qwen3.6-plus` | 262K | | | | | | $0.50 | $3 |
213
213
  | `llmgateway/qwen3.7-flash` | 1.0M | | | | | | $0.03 | $0.13 |
package/.docs/models/providers/neuralwatt.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Neuralwatt logo](https://models.dev/logos/neuralwatt.svg)Neuralwatt
4
4
 
5
- Access 18 Neuralwatt models through Mastra's model router. Authentication is handled automatically using the `NEURALWATT_API_KEY` environment variable.
5
+ Access 20 Neuralwatt models through Mastra's model router. Authentication is handled automatically using the `NEURALWATT_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Neuralwatt documentation](https://portal.neuralwatt.com/docs).
8
8
 
@@ -36,6 +36,8 @@ for await (const chunk of stream) {
36
36
 
37
37
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
38
  | --------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
+ | `neuralwatt/deepseek-v4-flash` | 1.0M | | | | | | $0.10 | $0.21 |
40
+ | `neuralwatt/gemma-4-31b` | 262K | | | | | | $0.14 | $0.42 |
39
41
  | `neuralwatt/glm-5.2` | 1.0M | | | | | | $1 | $5 |
40
42
  | `neuralwatt/glm-5.2-fast` | 1.0M | | | | | | $1 | $5 |
41
43
  | `neuralwatt/glm-5.2-flex` | 1.0M | | | | | | $0.72 | $2 |
package/.docs/models/providers/scaleway.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Scaleway logo](https://models.dev/logos/scaleway.svg)Scaleway
4
4
 
5
- Access 17 Scaleway models through Mastra's model router. Authentication is handled automatically using the `SCALEWAY_API_KEY` environment variable.
5
+ Access 14 Scaleway models through Mastra's model router. Authentication is handled automatically using the `SCALEWAY_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [Scaleway documentation](https://www.scaleway.com/en/docs/generative-apis/).
8
8
 
@@ -37,7 +37,6 @@ for await (const chunk of stream) {
37
37
  | Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
38
38
  | ---------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
39
39
  | `scaleway/bge-multilingual-gemma2` | 8K | | | | | | $0.10 | — |
40
- | `scaleway/gemma-3-27b-it` | 40K | | | | | | $0.25 | $0.50 |
41
40
  | `scaleway/gemma-4-26b-a4b-it` | 256K | | | | | | $0.25 | $0.50 |
42
41
  | `scaleway/glm-5.2` | 256K | | | | | | $2 | $6 |
43
42
  | `scaleway/gpt-oss-120b` | 128K | | | | | | $0.15 | $0.60 |
@@ -50,7 +49,6 @@ for await (const chunk of stream) {
50
49
  | `scaleway/qwen3-embedding-8b` | 33K | | | | | | $0.10 | — |
51
50
  | `scaleway/qwen3.5-397b-a17b` | 256K | | | | | | $0.60 | $4 |
52
51
  | `scaleway/qwen3.6-35b-a3b` | 128K | | | | | | $0.25 | $2 |
53
- | `scaleway/voxtral-small-24b-2507` | 32K | | | | | | $0.15 | $0.35 |
54
52
  | `scaleway/whisper-large-v3` | — | | | | | | $0.00 | — |
55
53
 
56
54
  ## Advanced configuration
package/.docs/models/providers/the-grid-ai.md CHANGED
@@ -2,12 +2,12 @@
2
2
 
3
3
  # ![The Grid AI logo](https://models.dev/logos/the-grid-ai.svg)The Grid AI
4
4
 
5
- Access 9 The Grid AI models through Mastra's model router. Authentication is handled automatically using the `THEGRIDAI_API_KEY` environment variable.
5
+ Access 9 The Grid AI models through Mastra's model router. Authentication is handled automatically using the `THEGRID_API_KEY` environment variable.
6
6
 
7
7
  Learn more in the [The Grid AI documentation](https://thegrid.ai/docs).
8
8
 
9
9
  ```bash
10
- THEGRIDAI_API_KEY=your-api-key
10
+ THEGRID_API_KEY=your-api-key
11
11
  ```
12
12
 
13
13
  ```typescript
@@ -57,7 +57,7 @@ const agent = new Agent({
57
57
  model: {
58
58
  url: "https://api.thegrid.ai/v1",
59
59
  id: "the-grid-ai/agent-max",
60
- apiKey: process.env.THEGRIDAI_API_KEY,
60
+ apiKey: process.env.THEGRID_API_KEY,
61
61
  headers: {
62
62
  "X-Custom-Header": "value"
63
63
  }
package/.docs/reference/cli/mastra.md CHANGED
@@ -412,12 +412,16 @@ mastra env vars pull
412
412
  mastra env vars pull <env> --output .env.staging
413
413
  ```
414
414
 
415
- `<env>` can be an environment name, slug, or ID, and can be omitted when the project has exactly one environment. The file is written with `0600` permissions.
415
+ `<env>` can be an environment name, slug, or ID, and can be omitted when the project has exactly one environment. The file is written with `0600` permissions. The command stops if the output file already exists. Pass `--force` to replace it.
416
416
 
417
417
  #### `-o, --output`
418
418
 
419
419
  File to write. Defaults to `.env`.
420
420
 
421
+ #### `-f, --force`
422
+
423
+ Replace an existing output file.
424
+
421
425
  ### `mastra env db`
422
426
 
423
427
  Manages databases attached to a project on Mastra platform. Databases are provisioned from a managed provider (for example Turso or Neon) and inject their connection env vars into deploys automatically.
package/.docs/reference/processors/processor-interface.md CHANGED
@@ -399,7 +399,7 @@ processLLMRequest?(
399
399
 
400
400
  **tracingContext** (`TracingContext`): Tracing context for observability.
401
401
 
402
- **writer** (`ProcessorStreamWriter`): Stream writer for emitting custom data chunks during streaming. Use writer.custom() to send transient UI signals.
402
+ **writer** (`ProcessorStreamWriter`): Stream writer for emitting custom data chunks during streaming. Call writer.custom() to emit a data-\* chunk.
403
403
 
404
404
  **abortSignal** (`AbortSignal`): Signal for cancelling the operation.
405
405
 
@@ -504,7 +504,7 @@ processAPIError?(args: ProcessAPIErrorArgs): Promise<ProcessAPIErrorResult | voi
504
504
 
505
505
  **abort** (`(reason?: string, options?: { retry?: boolean; metadata?: unknown }) => never`): Function to abort processing.
506
506
 
507
- **writer** (`ProcessorStreamWriter`): Stream writer for emitting custom data chunks during streaming. Use writer.custom() to send transient UI signals.
507
+ **writer** (`ProcessorStreamWriter`): Stream writer for emitting custom data chunks during streaming. Call writer.custom() to emit a data-\* chunk.
508
508
 
509
509
  **requestContext** (`RequestContext`): Request context passed through from the agent call.
510
510
 
@@ -961,6 +961,18 @@ await writer.custom({
961
961
  })
962
962
  ```
963
963
 
964
+ When memory is configured, custom `data-*` chunks emitted from `processOutputStream` or `processOutputResult` are saved as parts of the assistant message. Set `transient: true` on the chunk object to stream it without saving it to memory:
965
+
966
+ ```typescript
967
+ await writer.custom({
968
+ type: 'data-progress',
969
+ data: { status: 'Processing' },
970
+ transient: true,
971
+ })
972
+ ```
973
+
974
+ Pass `transient` as a property of the chunk, not as the second argument to `writer.custom()`. The second argument contains writer options such as `messageId`.
975
+
964
976
  By default, processors **don't** see `data-*` chunks in `processOutputStream` so they don't accidentally process tool telemetry or their own output. Opt in by setting `processDataParts: true` on the processor:
965
977
 
966
978
  ```typescript
package/CHANGELOG.md CHANGED
@@ -1,5 +1,19 @@
1
1
  # @mastra/mcp-docs-server
2
2
 
3
+ ## 1.2.13-alpha.4
4
+
5
+ ### Patch Changes
6
+
7
+ - Updated dependencies [[`322daa6`](https://github.com/mastra-ai/mastra/commit/322daa6d90552909204044790d850958f6745fed), [`cadaa13`](https://github.com/mastra-ai/mastra/commit/cadaa1372e1077c8e85eb64c5499ba8803caa323), [`06000d7`](https://github.com/mastra-ai/mastra/commit/06000d73712911572e913b8a83339270296d0a22), [`3de0188`](https://github.com/mastra-ai/mastra/commit/3de0188bfaf9a9c09c95fe322b53838cf52c70b6)]:
8
+ - @mastra/core@1.56.0-alpha.2
9
+
10
+ ## 1.2.13-alpha.2
11
+
12
+ ### Patch Changes
13
+
14
+ - Updated dependencies [[`c5e56ff`](https://github.com/mastra-ai/mastra/commit/c5e56ff3bcabdf062708f2d48744fec304df6792), [`4e35a56`](https://github.com/mastra-ai/mastra/commit/4e35a56cdf8d74a5ff6d5eda01f2c1deaf6cc7be)]:
15
+ - @mastra/core@1.56.0-alpha.1
16
+
3
17
  ## 1.2.13-alpha.1
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": "1.2.13-alpha.1",
3
+ "version": "1.2.13-alpha.4",
4
4
  "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -28,7 +28,7 @@
28
28
  "jsdom": "^26.1.0",
29
29
  "local-pkg": "^1.1.2",
30
30
  "zod": "^4.4.3",
31
- "@mastra/core": "1.56.0-alpha.0",
31
+ "@mastra/core": "1.56.0-alpha.2",
32
32
  "@mastra/mcp": "^1.15.0"
33
33
  },
34
34
  "devDependencies": {
@@ -47,7 +47,7 @@
47
47
  "vitest": "4.1.10",
48
48
  "@internal/lint": "0.0.119",
49
49
  "@internal/types-builder": "0.0.94",
50
- "@mastra/core": "1.56.0-alpha.0"
50
+ "@mastra/core": "1.56.0-alpha.2"
51
51
  },
52
52
  "homepage": "https://mastra.ai",
53
53
  "repository": {