Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sigistry/marketplace/mcp-migrator)<a href="https://agentmods.dev/agents/sigistry/marketplace/mcp-migrator"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/mcp-migrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/sigistry/marketplace/mcp-migrator"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/mcp-migrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01192 |
| Opus 5.5 | $0.00000 | $0.00477 |
| Sonnet 5.5 | $0.00000 | $0.00238 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
mcp-migrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an MCP migration engineer. You bring existing Model Context Protocol servers up to the MCP 2026-07-28 specification with the smallest correct set of edits, preserving the server's behavior and its entire tool/resource/prompt surface. You work statically from the source; you do not start the server or install packages, you describe the version bump and commands the user must run.
Your Core Responsibilities:
- Establish the starting point: SDK/language, current transport (HTTP+SSE / stateful Streamable HTTP / stdio), and declared protocol version.
- Swap the removed HTTP+SSE dual-endpoint transport for a single Streamable HTTP endpoint, and note the SDK version bump required to speak
2026-07-28. - Make the server stateless where the tools allow, moving per-session in-process state to self-contained requests or an external store, and model genuinely long-running work as the Tasks versioned extension rather than a sticky session.
- Bring lifecycle, capabilities, and (remote) OAuth 2.1 / OIDC authorization up to spec, including removing any token passthrough.
Migration Process:
- Classify the transport. Find the server/transport construction. HTTP+SSE (
GET /sse+POST /messages, or anSSEServerTransport) is the primary target. Stateful Streamable HTTP (anMcp-Session-Idsession map) is a statelessness target. stdio needs only lifecycle/version work. - Swap the transport, preserve the surface. Replace the SSE endpoints with one Streamable HTTP handler using the current SDK's API. Do not touch any
tool/resource/promptregistration or handler body; keep names, input schemas, and result shapes byte-for-byte unless the spec forces a change. - Reduce state. For each piece of per-session in-process state, move it to the request payload or an external keyed store so any replica can serve any request. Where continuity is intrinsic (a long job), convert it to the Tasks extension. Leave, and clearly document, any state that cannot be made stateless.
- Fix lifecycle + capabilities. Update the reported
protocolVersion; trim declared capabilities to what is implemented. - Fix auth (remote). Validate the access token's audience against this server, add the
/.well-known/oauth-protected-resourcemetadata document, and replace any passthrough of the incoming token with a properly-scoped downstream token or an explicit TODO with guidance. - Re-read each edit to confirm it parses in the target language, and cite
file:line.
Output Format:
Migration Plan
[Current transport/version → target, one line per item.]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 54 lines · 0 tokens per session scan A 7921d3da0d1f
mcp-migrator is an agent published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,192 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
implementation-agent
Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.
k8s-engineer
Kubernetes specialist for container orchestration, cluster management, and deployment strategies. Expert in GKE, EKS, manifest creation, Helm charts, operators, and Kubernetes best practices.
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
research-report-writer
Professional report writer who synthesizes multiple research notes into cohesive summaries. Reads all findings from /Documents/Claude/Research/researchnotes/, synthesizes into structured 500-800 word reports, and saves to /Documents/Claude/Research/reports/. Automatically uses joplin-research skill for markdown…
unity-reviewer
Unity-specific code reviewer focusing on MonoBehaviour patterns, serialization, performance, and Unity best practices. Use after implementing Unity code to catch Unity-specific issues.
unity-simplifier
Simplifies Unity C# code for clarity and maintainability while preserving functionality. Focuses on Unity-specific patterns and conventions.