agent-discover - npm Package Compare versions

Comparing version

1.3.8

1.3.9

+1

-1

agent-desk-plugin.json

		@@ -5,3 +5,3 @@ {
		"icon": "explore",
		"version": "1.3.8",
		"version": "1.3.9",
		"description": "MCP server registry — browse, install, configure, monitor",
		@@ -8,0 +8,0 @@ "ui": "./dist/ui/app.js",

+8

-1

CHANGELOG.md

		@@ -8,2 +8,9 @@ # Changelog

		## [1.3.9] - 2026-04-15

		### Changed

		- Bench README rewritten to reflect reproducible current-state numbers. Headline replaced with the scaling-of-first-turn-tokens table at N ∈ {10, 100, 1000, 3000} on OpenCode + gpt-5-mini: discover flat at ~20.8k, eager linear (20.9k → 32.4k → 160.9k → context overflow at N=3000). Adversarial CRUD pack now shows both arms at 100% accuracy; discover slightly more expensive on end-to-end multi-turn cost ($0.086 vs $0.068) due to `find_tool` output accumulation in conversation history. Added an explicit multi-turn cost caveat section.
		- Top-level README elevates the no-session-restart differentiator. Prominent callout directly under the intro noting that every MCP client today — including Claude Code — requires a full restart to pick up a newly registered MCP server, and agent-discover is the only path to register a new server and have it become discoverable in the same session.

		## [1.3.2] - 2026-04-12
		@@ -111,3 +118,3 @@
		- Hybrid retrieval (`searchToolsHybrid`). Brute-force cosine similarity over the entire embedded catalog + BM25 candidate union, scored 70% semantic / 30% lexical. Closes the natural-language gap that pure BM25 misses (e.g. "billing arrangement" → "subscription").
		- Bench harness under `bench/` comparing eager tool loading vs deferred discovery. Real Claude Code (`bench/drivers/cli.ts`) and OpenCode (`bench/drivers/opencode.ts`) drivers, isolated bench DB, scoring with `success` / `choice_accuracy` / `distractor_call_rate` / `refusal_rate` metrics, and a standalone `bench/rescore.ts` that re-applies the current scoring logic to captured event streams without spending fresh API tokens. Headline result at N=1000 on OpenCode + gpt-5-mini against an adversarial natural-language verb pack: discover 100% / 100% / 0% vs eager 80% / 80% / 20%, with ~27% lower per-turn token cost. Full results in `bench/README.md`.
		- Bench harness under `bench/` comparing eager tool loading vs deferred discovery. Real Claude Code (`bench/drivers/cli.ts`) and OpenCode (`bench/drivers/opencode.ts`) drivers, isolated bench DB, scoring with `success` / `choice_accuracy` / `distractor_call_rate` / `refusal_rate` metrics, and a standalone `bench/rescore.ts` that re-applies the current scoring logic to captured event streams without spending fresh API tokens. Headline reproducible result on OpenCode + gpt-5-mini: discover's first-turn input tokens are flat at ~20.8k across N ∈ {10, 100, 1000, 3000}; eager's grow linearly (20.9k → 32.4k → 160.9k → context overflow at N=3000, where eager can no longer complete the task). Full write-up in `bench/README.md`.

		@@ -114,0 +121,0 @@ ## [1.1.4] - 2026-04-09

+1

-1

package.json

		{
		"name": "agent-discover",
		"version": "1.3.8",
		"version": "1.3.9",
		"mcpName": "io.github.keshrath/agent-discover",
		@@ -5,0 +5,0 @@ "description": "MCP server registry and marketplace — discover, install, activate, and manage MCP tools on demand",

+3

-1

README.md

		@@ -12,2 +12,4 @@ # agent-discover

		> Every MCP client today — Claude Code, Cursor, Codex CLI, Aider, Continue, plain MCP clients — requires a full agent-session restart to pick up a newly registered MCP server. The tool catalog is frozen at startup. agent-discover is the only path to register a new server and have it become discoverable in the same running session. This is the one differentiator that survives against every host, even those with their own built-in deferred-tool loaders.

		Search spans the official MCP registry, npm, and PyPI in one query, so popular servers that aren't in the official index (Microsoft `@playwright/mcp`, `@modelcontextprotocol/server-*`, `mcp-server-fetch`, `mcp-server-git`, …) all show up.
		@@ -64,3 +66,3 @@
		- Declarative setup file -- set `AGENT_DISCOVER_SETUP_FILE` to a JSON file listing servers to ensure-registered on startup. Idempotent (skips existing). Supports `auto_activate`, env var secret refs (`$VAR`), and tags. Automatically also reads a `.local.json` variant (e.g. `discover-setup.local.json`) for machine-specific servers with secrets. New `registry({ action: "sync" })` MCP action and `POST /api/sync` REST endpoint for on-demand re-read.
		- Bench harness -- under `bench/`, comparing eager tool loading vs deferred discovery against real Claude Code and OpenCode hosts. Headline result at N=1000 against an adversarial natural-language verb pack: discover 100% accuracy + 27% lower per-turn token cost vs eager 80% accuracy. See [`bench/README.md`](bench/README.md).
		- Bench harness -- under `bench/`, comparing eager tool loading vs deferred discovery against real OpenCode + gpt-5-mini. Reproducible structural result: discover's first-turn input tokens are flat in N (~20.8k across N ∈ {10, 100, 1000, 3000}); eager's grow linearly (20.9k → 32.4k → 160.9k → context overflow at N=3000). End-to-end accuracy and multi-turn cost numbers are noisier and model-dependent — see [`bench/README.md`](bench/README.md) for what reproduces and what doesn't.

		@@ -67,0 +69,0 @@ ---

		@@ -12,2 +12,4 @@ # agent-discover

		> Every MCP client today — Claude Code, Cursor, Codex CLI, Aider, Continue, plain MCP clients — requires a full agent-session restart to pick up a newly registered MCP server. The tool catalog is frozen at startup. agent-discover is the only path to register a new server and have it become discoverable in the same running session. This is the one differentiator that survives against every host, even those with their own built-in deferred-tool loaders.

		Search spans the official MCP registry, npm, and PyPI in one query, so popular servers that aren't in the official index (Microsoft `@playwright/mcp`, `@modelcontextprotocol/server-*`, `mcp-server-fetch`, `mcp-server-git`, …) all show up.
		@@ -64,3 +66,3 @@
		- Declarative setup file -- set `AGENT_DISCOVER_SETUP_FILE` to a JSON file listing servers to ensure-registered on startup. Idempotent (skips existing). Supports `auto_activate`, env var secret refs (`$VAR`), and tags. Automatically also reads a `.local.json` variant (e.g. `discover-setup.local.json`) for machine-specific servers with secrets. New `registry({ action: "sync" })` MCP action and `POST /api/sync` REST endpoint for on-demand re-read.
		- Bench harness -- under `bench/`, comparing eager tool loading vs deferred discovery against real Claude Code and OpenCode hosts. Headline result at N=1000 against an adversarial natural-language verb pack: discover 100% accuracy + 27% lower per-turn token cost vs eager 80% accuracy. See [`bench/README.md`](bench/README.md).
		- Bench harness -- under `bench/`, comparing eager tool loading vs deferred discovery against real OpenCode + gpt-5-mini. Reproducible structural result: discover's first-turn input tokens are flat in N (~20.8k across N ∈ {10, 100, 1000, 3000}); eager's grow linearly (20.9k → 32.4k → 160.9k → context overflow at N=3000). End-to-end accuracy and multi-turn cost numbers are noisier and model-dependent — see [`bench/README.md`](bench/README.md) for what reproduces and what doesn't.

		@@ -67,0 +69,0 @@ ---

agent-discover - npm Package Compare versions

New alerts

Fixed alerts

Improved metrics