MCP server · Dyno

dyno-mcp.yml

Dyno publishes NO MCP server. This file is an API Evangelist CANDIDATE tool surface derived from the provider's OpenAPI, offered as a design sketch — it is NOT wired as a type: MCPServer pointer in apis.yml, because asserting an MCP server the provider does not run would be a false claim. What Dyno DOES publish for agents is a Claude Code Agent Skill and plugin over its CLI (see skills/_index.yml), which is a different, CLI-mediated agent surface.

View descriptor → Dyno provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

⚠ Proposed MCP surface. No official hosted MCP server was found for Dyno. The tools below are a candidate set derived from this provider's API, and the link points at the source descriptor rather than a live server. If Dyno publishes an official server, this page will update to it on the next build.

Provider: Dyno Type: Candidate descriptor Transport: Host: raw.githubusercontent.com

Descriptor

https://raw.githubusercontent.com/api-evangelist/dyno/refs/heads/main/mcp/dyno-mcp.yml

Candidate descriptor · transport

Tools

list_datasets — List protein structure datasets
get_dataset — Get one dataset
create_ingest_session — Start a multi-file structure upload
finalize_ingest_session — Finalize an upload into a dataset
submit_job — Submit a biomodal job (20 job types incl. filter_pipeline)
submit_batch_jobs — Submit a batch of jobs
get_job_status — Poll job status and progress
list_jobs — List recent jobs with status counts
cancel_job — Cancel a running job
get_job_scores — Get a signed URL for a job's scores CSV
get_dataset_scores — Get a signed URL for a dataset's scores
get_quota — Read current job quota and usage
list_protocols — Browse shareable workflow protocols
recommend_protocols — Recommend protocols for an intent
fork_protocol — Fork a protocol
plan_and_execute_protocol — Plan and execute a workflow from a protocol
get_workflow_run_status — Poll a workflow run
get_run_assets — List assets produced by a run
download_artifact — Get a signed download URL for an artifact
get_tutorial — Provision the PD-L1 tutorial dataset and fixture URLs

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.