From 30e9f0504c15fbfe268bff0119b1487b18af5866 Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Fri, 26 Jun 2026 22:35:34 +0000
Subject: [PATCH] chore: version packages

---
 .changeset/ai-autopilot-quality-pass.md       | 10 -----
 .changeset/ai-sdk-cache-seam.md               | 13 ------
 .changeset/ai-sdk-drop-doctor-subpath.md      |  9 ----
 .changeset/ai-sdk-drop-orm-subpaths.md        |  9 ----
 ...-sdk-export-cache-registry-eval-helpers.md |  7 ----
 .changeset/ai-sdk-quality-pass.md             |  5 ---
 .changeset/ai-sdk-storage-seam.md             |  9 ----
 .changeset/ai-skills-quality-pass.md          | 12 ------
 .changeset/mcp-quality-pass.md                | 10 -----
 packages/ai-autopilot/CHANGELOG.md            | 19 +++++++++
 packages/ai-autopilot/package.json            |  2 +-
 packages/ai-mcp/CHANGELOG.md                  | 12 ++++++
 packages/ai-mcp/package.json                  |  2 +-
 packages/ai-sdk/CHANGELOG.md                  | 41 +++++++++++++++++++
 packages/ai-sdk/package.json                  |  2 +-
 packages/ai-skills/CHANGELOG.md               | 23 +++++++++++
 packages/ai-skills/package.json               |  2 +-
 packages/mcp/CHANGELOG.md                     | 11 +++++
 packages/mcp/package.json                     |  2 +-
 19 files changed, 111 insertions(+), 89 deletions(-)
 delete mode 100644 .changeset/ai-autopilot-quality-pass.md
 delete mode 100644 .changeset/ai-sdk-cache-seam.md
 delete mode 100644 .changeset/ai-sdk-drop-doctor-subpath.md
 delete mode 100644 .changeset/ai-sdk-drop-orm-subpaths.md
 delete mode 100644 .changeset/ai-sdk-export-cache-registry-eval-helpers.md
 delete mode 100644 .changeset/ai-sdk-quality-pass.md
 delete mode 100644 .changeset/ai-sdk-storage-seam.md
 delete mode 100644 .changeset/ai-skills-quality-pass.md
 delete mode 100644 .changeset/mcp-quality-pass.md

diff --git a/.changeset/ai-autopilot-quality-pass.md b/.changeset/ai-autopilot-quality-pass.md
deleted file mode 100644
index ea0bc3a..0000000
--- a/.changeset/ai-autopilot-quality-pass.md
+++ /dev/null
@@ -1,10 +0,0 @@
----
-"@gemstack/ai-autopilot": patch
----
-
-Quality + docs pass for ai-autopilot:
-
-- `Supervisor` now validates its options at construction (`plan` must be a function, `workers` is required, `concurrency`/`maxSubtasks` must be positive integers) and `run()` rejects an empty task, so misconfiguration fails fast with a clear message instead of deep in a planner call.
-- An `onEvent` callback that throws is now isolated (logged and swallowed) so an observer bug can no longer abort a supervised run.
-- Corrected the `SupervisorRun.usage` docs: it aggregates dispatched-subtask usage only (the `Planner`/`Synthesizer` contracts return data, not usage, so planning/synthesis spend isn't observable).
-- Clarified that `maxSubtasks` and `budget` are optional, marked the internal `runPool` helper `@internal`, and added JSDoc examples.
diff --git a/.changeset/ai-sdk-cache-seam.md b/.changeset/ai-sdk-cache-seam.md
deleted file mode 100644
index 6685c40..0000000
--- a/.changeset/ai-sdk-cache-seam.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-"@gemstack/ai-sdk": minor
----
-
-Decouple the cache-backed run stores from `@rudderjs/cache` (epic: framework-agnostic engine).
-
-`CachedAgentRunStore` and `CachedSubAgentRunStore` no longer lazy-import `@rudderjs/cache` or read a global `CacheRegistry`. They now take a required, caller-supplied cache via `{ cache }`, typed against the new exported `CacheAdapter` contract (a 3-method interface: `get` / `set` / `forget`). Bring any cache (redis, Memcached, a `Map`, a framework's cache).
-
-**Breaking (0.x):**
-- `new CachedAgentRunStore()` / `new CachedSubAgentRunStore()` with no cache now throw; pass `{ cache }`. (All in-repo and documented usage already passes it.)
-- Default key prefixes changed from `rudderjs:ai:*` to `gemstack:ai:*`. These guard 5-minute-TTL ephemeral run snapshots, so the only effect on upgrade is that in-flight parked runs fall back to "not found" once (they self-heal). Override `keyPrefix` to keep the old value if needed.
-
-Also made the Google prompt-cache registry fully neutral (it already accepted a BYO store): it now uses the shared `CacheAdapter` type and a `gemstack:ai:google-cache:` key prefix, with no `@rudderjs/cache` references.
diff --git a/.changeset/ai-sdk-drop-doctor-subpath.md b/.changeset/ai-sdk-drop-doctor-subpath.md
deleted file mode 100644
index 7a736f2..0000000
--- a/.changeset/ai-sdk-drop-doctor-subpath.md
+++ /dev/null
@@ -1,9 +0,0 @@
----
-"@gemstack/ai-sdk": minor
----
-
-Remove the `@gemstack/ai-sdk/doctor` subpath (epic: framework-agnostic engine).
-
-The AI doctor check registered into `@rudderjs/console`'s doctor registry, coupling the agnostic engine to the Rudder CLI. It has moved to the Rudder binding `@rudderjs/ai/doctor` (same import path on that package). The `./doctor` export is removed here.
-
-**Breaking (0.x):** importing `@gemstack/ai-sdk/doctor` no longer resolves; use `@rudderjs/ai/doctor`. (The `@rudderjs/console` peer stays for now — `make:agent` and the `/server` provider still use it until they relocate too.)
diff --git a/.changeset/ai-sdk-drop-orm-subpaths.md b/.changeset/ai-sdk-drop-orm-subpaths.md
deleted file mode 100644
index c867575..0000000
--- a/.changeset/ai-sdk-drop-orm-subpaths.md
+++ /dev/null
@@ -1,9 +0,0 @@
----
-"@gemstack/ai-sdk": minor
----
-
-Decouple from `@rudderjs/orm` (epic: framework-agnostic engine).
-
-The ORM-backed store subpaths `@gemstack/ai-sdk/conversation-orm`, `/memory-orm`, `/budget-orm`, and `/memory-embedding` are **removed** from this package. They imported `@rudderjs/orm`, coupling the agnostic engine to the Rudder ORM, so they have moved to the Rudder binding `@rudderjs/ai` under the same subpath names (`@rudderjs/ai/conversation-orm`, etc.). The `@rudderjs/orm` peer dependency is dropped.
-
-**Breaking (0.x):** update imports from `@gemstack/ai-sdk/{conversation-orm,memory-orm,budget-orm,memory-embedding}` to `@rudderjs/ai/{...}`. The relocated implementations are unchanged and still implement the neutral `ConversationStore` / `UserMemory` / `BudgetStorage` contracts, which remain exported from `@gemstack/ai-sdk`. Non-Rudder apps implement those contracts against their own persistence, or use the in-memory defaults.
diff --git a/.changeset/ai-sdk-export-cache-registry-eval-helpers.md b/.changeset/ai-sdk-export-cache-registry-eval-helpers.md
deleted file mode 100644
index 25a933a..0000000
--- a/.changeset/ai-sdk-export-cache-registry-eval-helpers.md
+++ /dev/null
@@ -1,7 +0,0 @@
----
-"@gemstack/ai-sdk": minor
----
-
-Export `GoogleCacheRegistry` (+ `GoogleCacheRegistryOptions` / `CacheStoreLike`) from the main entry, and `defaultFixturesDir` / `readFixture` / `writeFixture` from the `./eval` subpath.
-
-These were gemstack-internal symbols that framework bindings could not reach against a published build. Surfacing them lets a binding construct the Gemini context-cache registry with its own `CacheAdapter` (`new GoogleCacheRegistry({ store })`) and lets an `ai:eval` CLI binding read/write recorded fixtures. Purely additive; unblocks relocating the `/server` provider and the `ai-eval` command to the Rudder side.
diff --git a/.changeset/ai-sdk-quality-pass.md b/.changeset/ai-sdk-quality-pass.md
deleted file mode 100644
index accb0a1..0000000
--- a/.changeset/ai-sdk-quality-pass.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"@gemstack/ai-sdk": patch
----
-
-Quality pass for ai-sdk: rebrand the error/log message prefix from the migration leftover `[Rudder AI]` to `[ai-sdk]` (108 messages across 38 modules), matching the sibling packages' package-name prefix convention, and fix the "file an issue" URL in the Bedrock provider to point at `gemstack-land/gemstack`. No API or behavior change beyond the message text.
diff --git a/.changeset/ai-sdk-storage-seam.md b/.changeset/ai-sdk-storage-seam.md
deleted file mode 100644
index d591963..0000000
--- a/.changeset/ai-sdk-storage-seam.md
+++ /dev/null
@@ -1,9 +0,0 @@
----
-"@gemstack/ai-sdk": minor
----
-
-Decouple `ImageGenerator.store()` / `AudioGenerator.store()` from `@rudderjs/storage` (epic: framework-agnostic engine).
-
-Both `.store()` helpers no longer lazy-import `@rudderjs/storage`. They now take a required, caller-supplied storage via a new exported `StorageAdapter` contract (a one-method interface: `put(path, bytes)`). Implement it against any blob store (S3, GCS, the filesystem, a framework's storage layer).
-
-**Breaking (0.x):** `.store(path)` is now `.store(path, storage)`. Migrate `await ImageGenerator.of(p).store('out.png')` to `await ImageGenerator.of(p).store('out.png', storage)` where `storage` satisfies `StorageAdapter`. A Rudder app wraps `@rudderjs/storage` in a ~3-line adapter.
diff --git a/.changeset/ai-skills-quality-pass.md b/.changeset/ai-skills-quality-pass.md
deleted file mode 100644
index a099b86..0000000
--- a/.changeset/ai-skills-quality-pass.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-"@gemstack/ai-skills": minor
----
-
-Quality + docs pass for ai-skills:
-
-- `SkillRegistry.discover()` no longer aborts the whole scan when a single `SKILL.md` is unreadable or malformed; the bad bundle is skipped and the rest are still indexed. Pass `discover(root, { onError })` to observe what was skipped. This restores the documented "index hundreds of skills safely" contract.
-- Skill `name` is now validated at parse time against `[a-zA-Z0-9_-]` instead of being silently mangled later at compose time, so invalid names fail fast with a clear message.
-- `load()` on an undiscovered name now lists the available skill names (or hints to call `discover()` first).
-- `loadSkill()` distinguishes a missing `SKILL.md` from an unreadable one.
-- Deduplicated the internal `fileExists`/`isDirectory` helpers into a shared module.
-- README: clarified that the tools module is loaded compiled (`tools.js`/`.mjs`/`.cjs`, not `tools.ts`), and added a direct `loadSkill()` usage example.
diff --git a/.changeset/mcp-quality-pass.md b/.changeset/mcp-quality-pass.md
deleted file mode 100644
index ea76560..0000000
--- a/.changeset/mcp-quality-pass.md
+++ /dev/null
@@ -1,10 +0,0 @@
----
-"@gemstack/mcp": patch
----
-
-Quality + docs pass for mcp:
-
-- OAuth: reject an empty bearer token (`Authorization: Bearer ` with no value) up front with a `401 invalid_token` instead of forwarding an empty string to `verifyToken`.
-- Errors thrown when a `@Handle` dependency fails to resolve now chain the original via `{ cause }`.
-- Documented `McpResponse.text/json/error` (and when to prefer `error()` over throwing); neutralized framework-specific wording in the OAuth core docs.
-- README: completed the OAuth 2.1 section (a real `jose`-based `verifyToken`, and that `oauth2McpMiddleware` + `registerOAuth2Metadata` must both be wired), softened the origin framing.
diff --git a/packages/ai-autopilot/CHANGELOG.md b/packages/ai-autopilot/CHANGELOG.md
index 444f8fd..fbf7a15 100644
--- a/packages/ai-autopilot/CHANGELOG.md
+++ b/packages/ai-autopilot/CHANGELOG.md
@@ -1,5 +1,24 @@
 # @gemstack/ai-autopilot
 
+## 0.1.1
+
+### Patch Changes
+
+- 81fe17b: Quality + docs pass for ai-autopilot:
+
+  - `Supervisor` now validates its options at construction (`plan` must be a function, `workers` is required, `concurrency`/`maxSubtasks` must be positive integers) and `run()` rejects an empty task, so misconfiguration fails fast with a clear message instead of deep in a planner call.
+  - An `onEvent` callback that throws is now isolated (logged and swallowed) so an observer bug can no longer abort a supervised run.
+  - Corrected the `SupervisorRun.usage` docs: it aggregates dispatched-subtask usage only (the `Planner`/`Synthesizer` contracts return data, not usage, so planning/synthesis spend isn't observable).
+  - Clarified that `maxSubtasks` and `budget` are optional, marked the internal `runPool` helper `@internal`, and added JSDoc examples.
+
+- Updated dependencies [e784b5d]
+- Updated dependencies [97ed299]
+- Updated dependencies [4fa5820]
+- Updated dependencies [cf28664]
+- Updated dependencies [035050e]
+- Updated dependencies [3cb13db]
+  - @gemstack/ai-sdk@0.4.0
+
 ## 0.1.0
 
 ### Minor Changes
diff --git a/packages/ai-autopilot/package.json b/packages/ai-autopilot/package.json
index 71ec7a9..db3ee25 100644
--- a/packages/ai-autopilot/package.json
+++ b/packages/ai-autopilot/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@gemstack/ai-autopilot",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Orchestration for @gemstack/ai-sdk agents: a Supervisor that plans, dispatches subagents (bounded concurrency + budget guardrails), and synthesizes the result.",
   "keywords": [
     "ai",
diff --git a/packages/ai-mcp/CHANGELOG.md b/packages/ai-mcp/CHANGELOG.md
index eead927..42f1d84 100644
--- a/packages/ai-mcp/CHANGELOG.md
+++ b/packages/ai-mcp/CHANGELOG.md
@@ -1,5 +1,17 @@
 # @gemstack/ai-mcp
 
+## 0.1.1
+
+### Patch Changes
+
+- Updated dependencies [e784b5d]
+- Updated dependencies [97ed299]
+- Updated dependencies [4fa5820]
+- Updated dependencies [cf28664]
+- Updated dependencies [035050e]
+- Updated dependencies [3cb13db]
+  - @gemstack/ai-sdk@0.4.0
+
 ## 0.1.0
 
 ### Minor Changes
diff --git a/packages/ai-mcp/package.json b/packages/ai-mcp/package.json
index ceff416..2c58895 100644
--- a/packages/ai-mcp/package.json
+++ b/packages/ai-mcp/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@gemstack/ai-mcp",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Bridge between @gemstack/ai-sdk Agents and Model Context Protocol servers: consume remote MCP tools as Agent tools, and expose an Agent as an MCP server.",
   "keywords": [
     "ai",
diff --git a/packages/ai-sdk/CHANGELOG.md b/packages/ai-sdk/CHANGELOG.md
index eba797f..d6d8876 100644
--- a/packages/ai-sdk/CHANGELOG.md
+++ b/packages/ai-sdk/CHANGELOG.md
@@ -1,5 +1,46 @@
 # @gemstack/ai-sdk
 
+## 0.4.0
+
+### Minor Changes
+
+- e784b5d: Decouple the cache-backed run stores from `@rudderjs/cache` (epic: framework-agnostic engine).
+
+  `CachedAgentRunStore` and `CachedSubAgentRunStore` no longer lazy-import `@rudderjs/cache` or read a global `CacheRegistry`. They now take a required, caller-supplied cache via `{ cache }`, typed against the new exported `CacheAdapter` contract (a 3-method interface: `get` / `set` / `forget`). Bring any cache (redis, Memcached, a `Map`, a framework's cache).
+
+  **Breaking (0.x):**
+
+  - `new CachedAgentRunStore()` / `new CachedSubAgentRunStore()` with no cache now throw; pass `{ cache }`. (All in-repo and documented usage already passes it.)
+  - Default key prefixes changed from `rudderjs:ai:*` to `gemstack:ai:*`. These guard 5-minute-TTL ephemeral run snapshots, so the only effect on upgrade is that in-flight parked runs fall back to "not found" once (they self-heal). Override `keyPrefix` to keep the old value if needed.
+
+  Also made the Google prompt-cache registry fully neutral (it already accepted a BYO store): it now uses the shared `CacheAdapter` type and a `gemstack:ai:google-cache:` key prefix, with no `@rudderjs/cache` references.
+
+- 97ed299: Remove the `@gemstack/ai-sdk/doctor` subpath (epic: framework-agnostic engine).
+
+  The AI doctor check registered into `@rudderjs/console`'s doctor registry, coupling the agnostic engine to the Rudder CLI. It has moved to the Rudder binding `@rudderjs/ai/doctor` (same import path on that package). The `./doctor` export is removed here.
+
+  **Breaking (0.x):** importing `@gemstack/ai-sdk/doctor` no longer resolves; use `@rudderjs/ai/doctor`. (The `@rudderjs/console` peer stays for now — `make:agent` and the `/server` provider still use it until they relocate too.)
+
+- 4fa5820: Decouple from `@rudderjs/orm` (epic: framework-agnostic engine).
+
+  The ORM-backed store subpaths `@gemstack/ai-sdk/conversation-orm`, `/memory-orm`, `/budget-orm`, and `/memory-embedding` are **removed** from this package. They imported `@rudderjs/orm`, coupling the agnostic engine to the Rudder ORM, so they have moved to the Rudder binding `@rudderjs/ai` under the same subpath names (`@rudderjs/ai/conversation-orm`, etc.). The `@rudderjs/orm` peer dependency is dropped.
+
+  **Breaking (0.x):** update imports from `@gemstack/ai-sdk/{conversation-orm,memory-orm,budget-orm,memory-embedding}` to `@rudderjs/ai/{...}`. The relocated implementations are unchanged and still implement the neutral `ConversationStore` / `UserMemory` / `BudgetStorage` contracts, which remain exported from `@gemstack/ai-sdk`. Non-Rudder apps implement those contracts against their own persistence, or use the in-memory defaults.
+
+- cf28664: Export `GoogleCacheRegistry` (+ `GoogleCacheRegistryOptions` / `CacheStoreLike`) from the main entry, and `defaultFixturesDir` / `readFixture` / `writeFixture` from the `./eval` subpath.
+
+  These were gemstack-internal symbols that framework bindings could not reach against a published build. Surfacing them lets a binding construct the Gemini context-cache registry with its own `CacheAdapter` (`new GoogleCacheRegistry({ store })`) and lets an `ai:eval` CLI binding read/write recorded fixtures. Purely additive; unblocks relocating the `/server` provider and the `ai-eval` command to the Rudder side.
+
+- 3cb13db: Decouple `ImageGenerator.store()` / `AudioGenerator.store()` from `@rudderjs/storage` (epic: framework-agnostic engine).
+
+  Both `.store()` helpers no longer lazy-import `@rudderjs/storage`. They now take a required, caller-supplied storage via a new exported `StorageAdapter` contract (a one-method interface: `put(path, bytes)`). Implement it against any blob store (S3, GCS, the filesystem, a framework's storage layer).
+
+  **Breaking (0.x):** `.store(path)` is now `.store(path, storage)`. Migrate `await ImageGenerator.of(p).store('out.png')` to `await ImageGenerator.of(p).store('out.png', storage)` where `storage` satisfies `StorageAdapter`. A Rudder app wraps `@rudderjs/storage` in a ~3-line adapter.
+
+### Patch Changes
+
+- 035050e: Quality pass for ai-sdk: rebrand the error/log message prefix from the migration leftover `[Rudder AI]` to `[ai-sdk]` (108 messages across 38 modules), matching the sibling packages' package-name prefix convention, and fix the "file an issue" URL in the Bedrock provider to point at `gemstack-land/gemstack`. No API or behavior change beyond the message text.
+
 ## 0.3.0
 
 ### Minor Changes
diff --git a/packages/ai-sdk/package.json b/packages/ai-sdk/package.json
index d1f58f1..e1a4bfb 100644
--- a/packages/ai-sdk/package.json
+++ b/packages/ai-sdk/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@gemstack/ai-sdk",
-  "version": "0.3.0",
+  "version": "0.4.0",
   "description": "AI engine: providers, agents, tools, streaming, middleware. The first GemStack package.",
   "keywords": [
     "ai",
diff --git a/packages/ai-skills/CHANGELOG.md b/packages/ai-skills/CHANGELOG.md
index 8d4a45d..27604a0 100644
--- a/packages/ai-skills/CHANGELOG.md
+++ b/packages/ai-skills/CHANGELOG.md
@@ -1,5 +1,28 @@
 # @gemstack/ai-skills
 
+## 0.2.0
+
+### Minor Changes
+
+- 3eb72d4: Quality + docs pass for ai-skills:
+
+  - `SkillRegistry.discover()` no longer aborts the whole scan when a single `SKILL.md` is unreadable or malformed; the bad bundle is skipped and the rest are still indexed. Pass `discover(root, { onError })` to observe what was skipped. This restores the documented "index hundreds of skills safely" contract.
+  - Skill `name` is now validated at parse time against `[a-zA-Z0-9_-]` instead of being silently mangled later at compose time, so invalid names fail fast with a clear message.
+  - `load()` on an undiscovered name now lists the available skill names (or hints to call `discover()` first).
+  - `loadSkill()` distinguishes a missing `SKILL.md` from an unreadable one.
+  - Deduplicated the internal `fileExists`/`isDirectory` helpers into a shared module.
+  - README: clarified that the tools module is loaded compiled (`tools.js`/`.mjs`/`.cjs`, not `tools.ts`), and added a direct `loadSkill()` usage example.
+
+### Patch Changes
+
+- Updated dependencies [e784b5d]
+- Updated dependencies [97ed299]
+- Updated dependencies [4fa5820]
+- Updated dependencies [cf28664]
+- Updated dependencies [035050e]
+- Updated dependencies [3cb13db]
+  - @gemstack/ai-sdk@0.4.0
+
 ## 0.1.0
 
 ### Minor Changes
diff --git a/packages/ai-skills/package.json b/packages/ai-skills/package.json
index 105aa23..5600049 100644
--- a/packages/ai-skills/package.json
+++ b/packages/ai-skills/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@gemstack/ai-skills",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "description": "Portable capability bundles for @gemstack/ai-sdk agents: load SKILL.md skills (instructions + tools + resources) and compose them onto an Agent.",
   "keywords": [
     "ai",
diff --git a/packages/mcp/CHANGELOG.md b/packages/mcp/CHANGELOG.md
index 9fc511b..fd0b762 100644
--- a/packages/mcp/CHANGELOG.md
+++ b/packages/mcp/CHANGELOG.md
@@ -1,5 +1,16 @@
 # @gemstack/mcp
 
+## 0.2.1
+
+### Patch Changes
+
+- 36f56e2: Quality + docs pass for mcp:
+
+  - OAuth: reject an empty bearer token (`Authorization: Bearer ` with no value) up front with a `401 invalid_token` instead of forwarding an empty string to `verifyToken`.
+  - Errors thrown when a `@Handle` dependency fails to resolve now chain the original via `{ cause }`.
+  - Documented `McpResponse.text/json/error` (and when to prefer `error()` over throwing); neutralized framework-specific wording in the OAuth core docs.
+  - README: completed the OAuth 2.1 section (a real `jose`-based `verifyToken`, and that `oauth2McpMiddleware` + `registerOAuth2Metadata` must both be wired), softened the origin framing.
+
 ## 0.2.0
 
 ### Minor Changes
diff --git a/packages/mcp/package.json b/packages/mcp/package.json
index e2c624e..4fe3fdb 100644
--- a/packages/mcp/package.json
+++ b/packages/mcp/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@gemstack/mcp",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "description": "Agent-agnostic framework for authoring Model Context Protocol (MCP) servers: tools, resources, prompts, decorators, OAuth 2.1, a framework-neutral HTTP handler, and a test client. The graduation of @rudderjs/mcp.",
   "keywords": [
     "mcp",