@mastra/mcp-docs-server 1.2.24-alpha.10 → 1.2.24-alpha.12
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/server/request-context.md +6 -5
- package/.docs/integrations/browsers/browser-viewer.md +10 -2
- package/.docs/models/providers/crossmodel.md +1 -1
- package/.docs/models/providers/edenai.md +2 -2
- package/.docs/models/providers/hyper.md +2 -1
- package/.docs/models/providers/kilo.md +3 -3
- package/.docs/models/providers/llmgateway-providers.md +1 -1
- package/.docs/models/providers/nano-gpt.md +3 -4
- package/.docs/reference/agent-controller/session.md +2 -0
- package/package.json +5 -5
|
@@ -259,7 +259,7 @@ Visit [createTool()](https://mastra.ai/reference/tools/create-tool) for a full l
|
|
|
259
259
|
|
|
260
260
|
## Reserved keys
|
|
261
261
|
|
|
262
|
-
Mastra reserves special context keys for
|
|
262
|
+
Mastra reserves special context keys for the server to read. The resource and thread keys take precedence over client-provided values: the server validates ownership and returns 403 errors when users attempt to access resources they don't own.
|
|
263
263
|
|
|
264
264
|
The easiest way to set `MASTRA_RESOURCE_ID_KEY` is via the `mapUserToResourceId` callback in auth config:
|
|
265
265
|
|
|
@@ -284,10 +284,11 @@ requestContext.set(MASTRA_RESOURCE_ID_KEY, user.id)
|
|
|
284
284
|
requestContext.set(MASTRA_THREAD_ID_KEY, threadId)
|
|
285
285
|
```
|
|
286
286
|
|
|
287
|
-
| Key
|
|
288
|
-
|
|
|
289
|
-
| `MASTRA_RESOURCE_ID_KEY`
|
|
290
|
-
| `MASTRA_THREAD_ID_KEY`
|
|
287
|
+
| Key | Purpose |
|
|
288
|
+
| --------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
289
|
+
| `MASTRA_RESOURCE_ID_KEY` | Forces all memory operations to use this resource ID. The server validates that accessed threads belong to this resource and returns 403 if not. |
|
|
290
|
+
| `MASTRA_THREAD_ID_KEY` | Forces thread operations to use this thread ID, overriding client-provided values |
|
|
291
|
+
| `MASTRA_MESSAGE_AUTHOR_KEY` | Names who sent a user message as `{ id, name?, avatarUrl? }`. Agent-controller sessions copy it onto every message the request sends as `providerMetadata.mastra.author`, so a thread shared by several people can show who wrote what. |
|
|
291
292
|
|
|
292
293
|
These keys are used to implement user isolation in multi-tenant applications. See [Authorization middleware](https://mastra.ai/docs/server/middleware) for usage examples.
|
|
293
294
|
|
|
@@ -95,7 +95,13 @@ export const mastra = new Mastra({
|
|
|
95
95
|
})
|
|
96
96
|
```
|
|
97
97
|
|
|
98
|
-
When the agent runs a CLI command
|
|
98
|
+
When the agent runs a browser CLI command, Mastra automatically launches Chrome, passes the CDP connection to the CLI, and starts streaming the screencast to Studio. For Browser Use, the agent can pass Python through stdin:
|
|
99
|
+
|
|
100
|
+
```bash
|
|
101
|
+
browser-use <<'PY'
|
|
102
|
+
print("Connected to the managed browser")
|
|
103
|
+
PY
|
|
104
|
+
```
|
|
99
105
|
|
|
100
106
|
## How it works
|
|
101
107
|
|
|
@@ -133,7 +139,9 @@ pip install browser-use
|
|
|
133
139
|
npx skills add browser-use/browser-use --skill browser-use
|
|
134
140
|
```
|
|
135
141
|
|
|
136
|
-
|
|
142
|
+
For direct stdin invocations (`browser-use`, `browseruse`, `browser`, or `bu`, optionally followed by `<` redirection or a heredoc), Mastra sets `BU_CDP_WS` to the managed browser's CDP URL and `BU_NAME` to a stable daemon name. The name is unique to the thread and browser endpoint, so repeated calls reuse the same daemon while different threads or endpoints stay isolated. Mastra preserves the stdin script without adding CLI arguments.
|
|
143
|
+
|
|
144
|
+
Legacy subcommands retain `--cdp-url` and `--session` injection for compatibility. These flags aren't added to stdin invocations.
|
|
137
145
|
|
|
138
146
|
### `browse`
|
|
139
147
|
|
|
@@ -72,7 +72,7 @@ for await (const chunk of stream) {
|
|
|
72
72
|
| `crossmodel/openai/gpt-5.5` | 1.1M | | | | | | $5 | $30 |
|
|
73
73
|
| `crossmodel/openai/gpt-5.5-pro` | 1.1M | | | | | | $30 | $180 |
|
|
74
74
|
| `crossmodel/openai/gpt-5.6-luna` | 1.1M | | | | | | $0.20 | $1 |
|
|
75
|
-
| `crossmodel/openai/gpt-5.6-sol` | 1.1M | | | | | | $
|
|
75
|
+
| `crossmodel/openai/gpt-5.6-sol` | 1.1M | | | | | | $4 | $20 |
|
|
76
76
|
| `crossmodel/openai/gpt-5.6-terra` | 1.1M | | | | | | $2 | $12 |
|
|
77
77
|
| `crossmodel/openai/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
78
78
|
| `crossmodel/qwen/qwen3.6-flash` | 1.0M | | | | | | $0.19 | $1 |
|
|
@@ -207,8 +207,8 @@ for await (const chunk of stream) {
|
|
|
207
207
|
| `edenai/perplexityai/sonar-deep-research` | 128K | | | | | | $2 | $8 |
|
|
208
208
|
| `edenai/perplexityai/sonar-pro` | 200K | | | | | | $3 | $15 |
|
|
209
209
|
| `edenai/perplexityai/sonar-reasoning-pro` | 128K | | | | | | $2 | $8 |
|
|
210
|
-
| `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.
|
|
211
|
-
| `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $
|
|
210
|
+
| `edenai/qwen/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.18 | $0.53 |
|
|
211
|
+
| `edenai/qwen/deepseek-v4-pro-0813` | 1.0M | | | | | | $0.58 | $2 |
|
|
212
212
|
| `edenai/qwen/qwen-max` | 33K | | | | | | $2 | $6 |
|
|
213
213
|
| `edenai/qwen/qwen-vl-max` | 131K | | | | | | $0.80 | $3 |
|
|
214
214
|
| `edenai/qwen/qwen-vl-plus` | 131K | | | | | | $0.21 | $0.63 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Charm Hyper
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 33 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Charm Hyper documentation](https://hyper.charm.land).
|
|
10
10
|
|
|
@@ -49,6 +49,7 @@ for await (const chunk of stream) {
|
|
|
49
49
|
| `hyper/glm-5.3` | 1.0M | | | | | | $2 | $5 |
|
|
50
50
|
| `hyper/glm-5.3-flash` | 1.0M | | | | | | $0.16 | $0.54 |
|
|
51
51
|
| `hyper/gpt-oss-120b` | 128K | | | | | | $0.19 | $0.70 |
|
|
52
|
+
| `hyper/inkling` | 1.0M | | | | | | $1 | $4 |
|
|
52
53
|
| `hyper/kimi-k2-thinking` | 262K | | | | | | $0.60 | $3 |
|
|
53
54
|
| `hyper/kimi-k2.5` | 262K | | | | | | $0.51 | $3 |
|
|
54
55
|
| `hyper/kimi-k2.6` | 262K | | | | | | $1 | $4 |
|
|
@@ -332,7 +332,7 @@ for await (const chunk of stream) {
|
|
|
332
332
|
| `kilo/qwen/qwen3-vl-8b-thinking` | 131K | | | | | | $0.18 | $2 |
|
|
333
333
|
| `kilo/qwen/qwen3.5-122b-a10b` | 262K | | | | | | $0.26 | $2 |
|
|
334
334
|
| `kilo/qwen/qwen3.5-27b` | 262K | | | | | | $0.20 | $2 |
|
|
335
|
-
| `kilo/qwen/qwen3.5-35b-a3b` |
|
|
335
|
+
| `kilo/qwen/qwen3.5-35b-a3b` | 256K | | | | | | $0.16 | $1 |
|
|
336
336
|
| `kilo/qwen/qwen3.5-397b-a17b` | 262K | | | | | | $0.39 | $2 |
|
|
337
337
|
| `kilo/qwen/qwen3.5-9b` | 262K | | | | | | $0.10 | $0.15 |
|
|
338
338
|
| `kilo/qwen/qwen3.5-flash-02-23` | 1.0M | | | | | | $0.07 | $0.26 |
|
|
@@ -371,12 +371,12 @@ for await (const chunk of stream) {
|
|
|
371
371
|
| `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
|
|
372
372
|
| `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
|
|
373
373
|
| `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
|
|
374
|
-
| `kilo/tencent/hy3` | 262K | | | | | | $0.
|
|
374
|
+
| `kilo/tencent/hy3` | 262K | | | | | | $0.08 | $0.33 |
|
|
375
375
|
| `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
|
|
376
376
|
| `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
377
377
|
| `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
|
|
378
378
|
| `kilo/thedrummer/skyfall-36b-v2` | 33K | | | | | | $0.55 | $0.80 |
|
|
379
|
-
| `kilo/thedrummer/unslopnemo-12b` |
|
|
379
|
+
| `kilo/thedrummer/unslopnemo-12b` | 1.0M | | | | | | $0.40 | $0.40 |
|
|
380
380
|
| `kilo/thinkingmachines/inkling` | 524K | | | | | | $0.95 | $4 |
|
|
381
381
|
| `kilo/thinkingmachines/inkling-small` | 524K | | | | | | $0.45 | $1 |
|
|
382
382
|
| `kilo/thinkingmachines/inkling-small:free` | 1.0M | | | | | | — | — |
|
|
@@ -165,7 +165,7 @@ for await (const chunk of stream) {
|
|
|
165
165
|
| `llmgateway-providers/cerebras/gpt-oss-120b` | 131K | | | | | | $0.35 | $0.75 |
|
|
166
166
|
| `llmgateway-providers/cerebras/llama-3.3-70b-instruct` | 128K | | | | | | $0.85 | $1 |
|
|
167
167
|
| `llmgateway-providers/cerebras/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.60 | $1 |
|
|
168
|
-
| `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 524K | | | | | | $0.
|
|
168
|
+
| `llmgateway-providers/consensusprotocol/deepseek-v4-flash` | 524K | | | | | | $0.05 | $0.10 |
|
|
169
169
|
| `llmgateway-providers/consensusprotocol/glm-5.3-flash` | 1.0M | | | | | | $0.10 | $0.25 |
|
|
170
170
|
| `llmgateway-providers/consensusprotocol/gpt-oss-20b` | 66K | | | | | | $0.04 | $0.19 |
|
|
171
171
|
| `llmgateway-providers/consensusprotocol/Qwen3.8-27B` | 33K | | | | | | $0.41 | $3 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# NanoGPT
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 591 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [NanoGPT documentation](https://docs.nano-gpt.com).
|
|
10
10
|
|
|
@@ -357,7 +357,6 @@ for await (const chunk of stream) {
|
|
|
357
357
|
| `nano-gpt/NousResearch/hermes-3-llama-3.1-70b` | 66K | | | | | | $0.41 | $0.41 |
|
|
358
358
|
| `nano-gpt/NousResearch/hermes-4-405b` | 128K | | | | | | $0.30 | $1 |
|
|
359
359
|
| `nano-gpt/NousResearch/hermes-4-405b:thinking` | 128K | | | | | | $0.30 | $1 |
|
|
360
|
-
| `nano-gpt/NousResearch/Hermes-4-70B:thinking` | 128K | | | | | | $0.20 | $0.40 |
|
|
361
360
|
| `nano-gpt/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF` | 16K | | | | | | $0.36 | $0.41 |
|
|
362
361
|
| `nano-gpt/nvidia/Llama-3.3-Nemotron-Super-49B-v1` | 128K | | | | | | $0.15 | $0.15 |
|
|
363
362
|
| `nano-gpt/nvidia/nemotron-3-nano-30b-a3b` | 262K | | | | | | $0.17 | $0.68 |
|
|
@@ -402,7 +401,7 @@ for await (const chunk of stream) {
|
|
|
402
401
|
| `nano-gpt/openai/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
403
402
|
| `nano-gpt/openai/gpt-6-astra-pro` | 1.1M | | | | | | $10 | $50 |
|
|
404
403
|
| `nano-gpt/openai/gpt-chat-latest` | 1.1M | | | | | | $2 | $10 |
|
|
405
|
-
| `nano-gpt/openai/gpt-latest` | 1.1M | | | | | | $
|
|
404
|
+
| `nano-gpt/openai/gpt-latest` | 1.1M | | | | | | $10 | $50 |
|
|
406
405
|
| `nano-gpt/openai/gpt-oss-120b` | 128K | | | | | | $0.35 | $0.75 |
|
|
407
406
|
| `nano-gpt/openai/gpt-oss-20b` | 128K | | | | | | $0.20 | $0.30 |
|
|
408
407
|
| `nano-gpt/openai/gpt-oss-safeguard-20b` | 128K | | | | | | $0.07 | $0.30 |
|
|
@@ -552,7 +551,7 @@ for await (const chunk of stream) {
|
|
|
552
551
|
| `nano-gpt/tencent/hy3` | 262K | | | | | | $0.07 | $0.26 |
|
|
553
552
|
| `nano-gpt/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
554
553
|
| `nano-gpt/TheDrummer/Anubis-70B-v1` | 66K | | | | | | $0.31 | $0.31 |
|
|
555
|
-
| `nano-gpt/TheDrummer/Anubis-70B-v1.1` |
|
|
554
|
+
| `nano-gpt/TheDrummer/Anubis-70B-v1.1` | 32K | | | | | | $0.31 | $0.31 |
|
|
556
555
|
| `nano-gpt/TheDrummer/Cydonia-24B-v2` | 33K | | | | | | $0.10 | $0.12 |
|
|
557
556
|
| `nano-gpt/TheDrummer/Cydonia-24B-v4` | 33K | | | | | | $0.20 | $0.24 |
|
|
558
557
|
| `nano-gpt/TheDrummer/Cydonia-24B-v4.1` | 131K | | | | | | $0.35 | $0.55 |
|
|
@@ -105,6 +105,8 @@ await session.sendMessage({
|
|
|
105
105
|
})
|
|
106
106
|
```
|
|
107
107
|
|
|
108
|
+
When `requestContext` carries `MASTRA_MESSAGE_AUTHOR_KEY`, the stored message names that sender under `content.providerMetadata.mastra.author`. See [Reserved keys](https://mastra.ai/docs/server/request-context).
|
|
109
|
+
|
|
108
110
|
#### `steer({ content, requestContext? })`
|
|
109
111
|
|
|
110
112
|
Queue steering content into an active run.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mastra/mcp-docs-server",
|
|
3
|
-
"version": "1.2.24-alpha.
|
|
3
|
+
"version": "1.2.24-alpha.12",
|
|
4
4
|
"description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -27,8 +27,8 @@
|
|
|
27
27
|
"jsdom": "^26.1.0",
|
|
28
28
|
"local-pkg": "^1.1.2",
|
|
29
29
|
"zod": "^4.4.3",
|
|
30
|
-
"@mastra/
|
|
31
|
-
"@mastra/
|
|
30
|
+
"@mastra/mcp": "^1.17.3",
|
|
31
|
+
"@mastra/core": "1.65.0-alpha.6"
|
|
32
32
|
},
|
|
33
33
|
"devDependencies": {
|
|
34
34
|
"@hono/node-server": "^2.0.0",
|
|
@@ -45,8 +45,8 @@
|
|
|
45
45
|
"typescript": "^7.0.2",
|
|
46
46
|
"vitest": "4.1.10",
|
|
47
47
|
"@internal/lint": "0.0.130",
|
|
48
|
-
"@
|
|
49
|
-
"@
|
|
48
|
+
"@internal/types-builder": "0.0.105",
|
|
49
|
+
"@mastra/core": "1.65.0-alpha.6"
|
|
50
50
|
},
|
|
51
51
|
"homepage": "https://mastra.ai",
|
|
52
52
|
"repository": {
|