modelcontextprotocol/typescript-sdk - Open Source PR Review Scorecard

The official TypeScript SDK for Model Context Protocol servers and clients

C-Rank Grade: A (Welcoming) - 61/100

External PR Merge Rate: 9%

Response Time: -

First Timer Success: 14%

Frequently Asked Questions

Is modelcontextprotocol/typescript-sdk welcoming to first-time open-source contributors?

modelcontextprotocol/typescript-sdk has a recorded first-timer success rate of 13.6%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.

How fast can I expect code review feedback on my pull request?

Maintainers in modelcontextprotocol/typescript-sdk respond to incoming external pull requests in approximately 0.0 hours on average. Keeping PRs focused on single tasks and ensuring tests pass helps maintainers review faster.

What does the 61.2 C-Rank™ score (A Tier) represent?

The C-Rank™ system evaluates GitHub projects on a 0–100 scale using real data: PR merge rates, review turnaround time, active maintainer presence, and first-time contributor success. A score of 61.2 places modelcontextprotocol/typescript-sdk in the A tier.

What is the external contributor pull request merge rate for modelcontextprotocol/typescript-sdk?

The external contributor pull request merge rate for modelcontextprotocol/typescript-sdk is 8.8%, based on public PR activity from non-core contributors.

Are there Good First Issues available in modelcontextprotocol/typescript-sdk?

modelcontextprotocol/typescript-sdk currently has 5 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".

modelcontextprotocol
modelcontextprotocol/typescript-sdkA•Welcoming13.4k
GitHub
Back to Explorer
modelcontextprotocol

modelcontextprotocol/typescript-sdk

13,429
Active (30d)A•Welcoming(61/100)TypeScript

The official TypeScript SDK for Model Context Protocol servers and clients

GitHub
Compare••
Jump to:

AI Maintainer Review Guidelines

Review Persona

Active Open-Source Maintainer

Warmth Score
7.8/10
Patience Score
8.2/10
Nitpick Rate
20%

Active maintainer team in modelcontextprotocol/typescript-sdk welcoming community pull requests and bug fixes.

Top PR Submission Do's

  • •Ensure code complies with repository style conventions
  • •Keep PRs focused and well-documented

Top PR Friction Pitfalls (Don'ts)

  • •Do not submit unlinked PRs without context
  • •Do not break existing automated test suites
Response Velocity
-
No reviewer activity recorded

Average Response Latency

Tracks hours until a maintainer leaves a review, comment, or PR response.

Merge Efficiency
8.8%
Selective PR acceptance rate

External Acceptance Rate

Percentage of community pull requests successfully merged into main.

First-Timer Success
13.6%
Accepts new contributor PRs

First PR Conversion

Rate at which developers submitting their first repository PR succeed.

Active Maintainers
86 core
Highly collaborative maintainer core
Diagnostic Health HUD
8.8%
Merge Gauge
13.6%
1st-Timer
Community Vibe8/100

Embed C-Rank Badge

Show contributors that your repository actively reviews and merges external pull requests.

GetMerged C-Rank badge for modelcontextprotocol/typescript-sdk
[![GetMerged C-Rank](https://getmerged.abhishekco.de/api/badge/modelcontextprotocol/typescript-sdk)](https://getmerged.abhishekco.de/modelcontextprotocol/typescript-sdk?utm_source=github&utm_medium=badge)

Active Good First Issues (5)

View on GitHub

Summary packages/middleware/node/test/streamableHttp.test.ts has tests that call reader.read() once and then assert the accumulated text contains multiple SSE events. On Node v26.7.0, fetch can deliver those SSE events in separate chunks, so the middleware behavior works but the tests fail before reading the later events. Reproduction Run pnpm install --frozen-lockfile Run pnpm build:all Run pnpm --filter @modelcontextprotocol/node test -- test/streamableHttp.test.ts Observed failures: should handle batch request messages with SSE stream for responses reads only the req-1 event and then fails before reading req-2. should store and replay MCP server tool notifications reads an earlier {} event and then fails before reading Second notification from MCP server. Suggested fix Read from the SSE stream until the expected event text appears or a short timeout/cancel occurs, instead of assuming multiple SSE events share one fetch chunk. I pushed a minimal branch here: https://github.com/js

📅 Opened Aug 14, 2026💬 4 comments
Quality: 50/100Contribute

What happened? Connecting to an unreachable host with versionNegotiation: { mode: "auto" } rejects with an SdkError whose cause is undefined. The underlying TypeError: fetch failed — and the DNS error beneath it that actually names the failure — is retained, but at error.data.cause. Anything walking the standard .cause chain stops at the SdkError. classifyNetworkError passes { cause: error } as the third argument: // dist/index.mjs:2400 return { kind: "error", error: new SdkError(SdkErrorCode.EraNegotiationFailed, `Version negotiation probe failed: ${describeError(error)}`, { cause: error }) }; But SdkError's third parameter is data, not ErrorOptions, and super() is called without it: // dist/src-D_zzAWoS.mjs:342 var SdkError = class extends Error { constructor(code, message, data) { super(message); // <- options never forwarded this.code = code; this.data = data; // <- the { cause } object lands here this.name = "SdkError"; stampErrorBrands(this, new.t

📅 Opened Aug 13, 2026💬 0 comments
Quality: 60/100Contribute

Summary On SDK v1 (still latest on npm as of this writing — 1.30.0), passing a ZodObject (z.object({...})) where the API expects a Zod raw shape ({ field: z.string() }) produces failure modes that are either silent or cryptic, depending on the version and the API used. None of them point the developer at the actual mistake, and neither the troubleshooting page nor the v1→v2 migration guide mentions these symptoms. I hit this while building scorm-mcp-server and lost the better part of a day on it: the server started fine, tools/list looked plausible, but every client silently stripped my tool arguments. I've since tested the behavior across v1 versions — full matrix below. Reproduction matrix Minimal repro: register one tool with inputSchema: z.object({ name: z.string() }) (instead of the raw shape { name: z.string() }), connect an in-memory client, call tools/list. SDK version registerTool + z.object() server.tool() (positional) + z.object() 1.12.0 → 1.21.0 ❌ tools/lis

📅 Opened Aug 9, 2026💬 4 comments
Quality: 50/100Contribute

Describe the bug When you cancel a request using AbortSignal, the error you get back has code: 'REQUEST_TIMEOUT' — the same code as an actual timeout. There's no way to tell them apart. I had logic like this in my app: if (error.code === SdkErrorCode.RequestTimeout) { showRetryMessage(); // was also firing on manual user cancellation } Both a real timeout and a deliberate controller.abort() hit the same fallback in cancel() inside protocol.ts (line ~910), which unconditionally wraps any non-SdkError reason as SdkErrorCode.RequestTimeout. To Reproduce import { Client } from '@modelcontextprotocol/client'; import { Server } from '@modelcontextprotocol/server'; import { InMemoryTransport, SdkError, SdkErrorCode } from '@modelcontextprotocol/core'; const [clientTransport, serverTransport] = InMemoryTransport.createLinkedPair(); const server = new Server({ name: 'test-server', version: '1.0' }); const client = new Client({ name: 'test-client', version: '1.0' }); // handler that hangs

📅 Opened May 28, 2026💬 5 comments
Quality: 30/100Contribute

While reading the v2 README, I noticed @modelcontextprotocol/fastify is published (packages/middleware/fastify/package.json has "private": false and the same 2.0.0-alpha.2 version as the other middleware packages) but absent from the README in three places: Overview (around line 32) — the parenthetical reads "(Express, Hono, Node.js HTTP)"; Fastify is omitted. Middleware packages section (around lines 49–52) — the bullet list documents @modelcontextprotocol/node, /express, and /hono with no /fastify entry. Installation (around lines 83–91) — npm install commands for node, express, and hono, with no fastify line. The other three middleware packages share the same private: false + 2.0.0-alpha.2 shape and are documented, so this looks like an oversight rather than intentional exclusion. The package already has its own packages/middleware/fastify/README.md. Happy to send a small docs-only PR adding fastify alongside the other three. Let me know if there's a reason fastify shoul

📅 Opened May 16, 2026💬 4 comments
Quality: 50/100Contribute
Looking for more TypeScript beginner tasks?Explore TypeScript GFI

Contributor Community Vibe Feedback

Rate what actually matters after opening a pull request here.

Have you contributed to this repo?

Rate your first-hand PR experience (review speed, maintainer responsiveness, and onboarding ease) to help other contributors.

3 ratings required
Maintainer helpfulness
Review speed
Beginner friendliness

Contributor Compatibility & Review Speed Analysis for modelcontextprotocol/typescript-sdk

When evaluating whether to contribute to modelcontextprotocol/typescript-sdk, response velocity and maintainer engagement are crucial. GetMerged continuously tracks pull request trajectories, first-comment latency, and code review rounds to help developers avoid submitting pull requests to backlogged repositories.

Currently, maintainers of modelcontextprotocol/typescript-sdk acknowledge new external contributions in approximately -. Out of all submitted pull requests from non-core authors in the last 180-day window, 8.8% were successfully merged into the primary branch.

Frequently Asked Questions - Contributing to modelcontextprotocol/typescript-sdk

01

Is modelcontextprotocol/typescript-sdk welcoming to first-time open-source contributors?

modelcontextprotocol/typescript-sdk has a recorded first-timer success rate of 13.6%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.

02

How fast can I expect code review feedback on my pull request?

The initial maintainer response time averages ~-. Keeping PRs scoped to single concerns and ensuring CI checks succeed will optimize review turnaround.

03

What does the 61.2 C-Rank™ score represent?

The C-Rank™ index scores repositories on a 0 to 100 scale using an objective formula: external PR merge rates, initial response speed, active maintainer count, and first-time contributor retention. A score of 61.2 places modelcontextprotocol/typescript-sdk in the Welcoming tier.

04

What is the external contributor pull request merge rate for modelcontextprotocol/typescript-sdk?

The external pull request merge rate is 8.8%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.

05

Are there beginner Good First Issues open in modelcontextprotocol/typescript-sdk?

Yes, modelcontextprotocol/typescript-sdk currently has 5 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.

GetMerged C-Rank™ Indexing Standard

All metrics displayed for modelcontextprotocol/typescript-sdk are automatically retrieved via the public GitHub API and recalculated daily. Insider pull requests submitted by repository owners or organization members are excluded from merge rate calculations to preserve objective external contributor statistics.