Dyno website screenshot

Dyno

Dyno Therapeutics is an AI and biotechnology company building high-performance gene delivery technologies to unlock the potential of next-generation genetic medicine. Using its CapsidMap platform, which combines machine learning with high-throughput in vivo measurement, Dyno designs novel adeno-associated virus (AAV) capsids with improved tissue targeting, immune evasion, manufacturability, and payload capacity. Alongside its capsid partnerships, Dyno operates a public developer platform — Dyno Psi-Phi at design.dynotx.com — that exposes a REST API for agentic protein design: submit structure-prediction, inverse-folding and binder-scoring jobs against GPU-backed open models (AlphaFold2, ESMFold, ProteinMPNN, Boltz, ESM-2, RFDiffusion3, BoltzGen, OpenFold3), track job status, and retrieve scored results. The platform ships a first-party Python CLI (dyno-phi), an MIT-licensed open-source repository, and a provider-published Claude Code Agent Skill. Founded on research from George Church's lab at Harvard, Dyno is headquartered in Watertown, Massachusetts, and is an a16z Bio+Health portfolio company.

Dyno publishes 1 API on the APIs.io network: Phi — Protein Design API. Tagged areas include Company, Biotechnology, Gene Therapy, Genetic Medicine, and Gene Delivery.

Dyno’s developer surface includes documentation, API reference, getting-started guide, engineering blog, support, signup flow, CLI, and 25 more developer resources.

50.8/100 developing ▬ flat Agent 38/100 agent ready Full breakdown ↓
scored 2026-08-20 · rubric v0.12.0
1 APIs 1 MCP Servers
CompanyBiotechnologyGene TherapyGenetic MedicineGene DeliveryAAV CapsidArtificial IntelligenceMachine-LearningDrug DiscoveryHealthcareProtein DesignProtein Structure PredictionBioinformaticsComputational BiologyAgentic AILife Sciences

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-20 · rubric v0.12.0
Composite quality — 50.8/100 · developing
Contract Quality 11.0 / 21
Developer Ergonomics 14.6 / 17
Access Clarity 5.8 / 17
Operational Transparency 2.0 / 11
Contract Governance 1.7 / 10
Discoverability 6.5 / 9
Regulatory Posture 4.7 / 15
Agent readiness — 38/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 10
Documented Reversibility 0 / 6
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
Regulatory Posture applies to this provider. Its tags matched the Health regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.
The six quality facets above are damped to 85 points between them, because the conditional facet above carries the other 15. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 85% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/dyno: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

Dyno Phi — Protein Design API

Phi is a biomodal computation platform for protein design. The REST API lets a caller create datasets from PDB/CIF structures, submit structure-prediction and sequence-design jo...

Open Collections 1

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

Dyno MCP Server

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: ...

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Dyno Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Dyno Rate Limits

0 limits

RATE LIMITS

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Dyno Authentication

apiKey/http-bearer/oidc-session · 3 schemes

SECURITY

Dyno Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 4

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Build 5

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 3

Status, limits, changes, and where to get help

Commercial 4

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Other 2

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: dyno
accessModel:
  pricing: unknown
  onboarding: self-service
  trial: true
  try_now: true
  public: true
  label: Self-service signup, API key from dashboard
  confidence: medium
  source:
  - https://design.dynotx.com/
  - https://design.dynotx.com/cli
  generated: '2026-08-10'
  method: searched
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/dyno.png
name: Dyno
description: 'Dyno Therapeutics is an AI and biotechnology company building high-performance gene delivery technologies to
  unlock the potential of next-generation genetic medicine. Using its CapsidMap platform, which combines machine learning
  with high-throughput in vivo measurement, Dyno designs novel adeno-associated virus (AAV) capsids with improved tissue targeting,
  immune evasion, manufacturability, and payload capacity. Alongside its capsid partnerships, Dyno operates a public developer
  platform — Dyno Psi-Phi at design.dynotx.com — that exposes a REST API for agentic protein design: submit structure-prediction,
  inverse-folding and binder-scoring jobs against GPU-backed open models (AlphaFold2, ESMFold, ProteinMPNN, Boltz, ESM-2,
  RFDiffusion3, BoltzGen, OpenFold3), track job status, and retrieve scored results. The platform ships a first-party Python
  CLI (dyno-phi), an MIT-licensed open-source repository, and a provider-published Claude Code Agent Skill. Founded on research
  from George Church''s lab at Harvard, Dyno is headquartered in Watertown, Massachusetts, and is an a16z Bio+Health portfolio
  company.'
url: https://raw.githubusercontent.com/api-evangelist/dyno/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- a16z
x-tier: profile
x-tier-reason: public-api-discovered
x-industry: biotechnology
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-08-10'
tags:
- Company
- Biotechnology
- Gene Therapy
- Genetic Medicine
- Gene Delivery
- AAV Capsid
- Artificial Intelligence
- Machine-Learning
- Drug Discovery
- Healthcare
- Protein Design
- Protein Structure Prediction
- Bioinformatics
- Computational Biology
- Agentic AI
- Life Sciences
tags_raw:
- Company
- Biotechnology
- Gene Therapy
- Genetic Medicine
- Gene Delivery
- AAV Capsid
- Artificial Intelligence
- Machine Learning
- Drug Discovery
- Healthcare
- Protein Design
- Protein Structure Prediction
- Bioinformatics
- Computational Biology
- Agentic AI
- Life Sciences
apis:
- name: Dyno Phi — Protein Design API
  description: Phi is a biomodal computation platform for protein design. The REST API lets a caller create datasets from
    PDB/CIF structures, submit structure-prediction and sequence-design jobs across twenty biomodal job types (ESMFold, AlphaFold2
    multimer, ProteinMPNN, Boltz, Chai-1, ESM-2, RFDiffusion3, BoltzGen, OpenFold3, BindCraft, AF2Rank, TM-score and more),
    compose and execute multi-step workflows and protocols, register agents and tools, poll job status, stream job logs, and
    download scored results and artifacts. Authentication is a static API key; per-user and per-organization job quotas are
    exposed through the API itself.
  humanURL: https://design.dynotx.com/docs
  baseURL: https://api.dyno-agents.app
  tags:
  - Protein Design
  - Structure Prediction
  - Machine-Learning
  - Job
  - Workflows
  tags_raw:
  - Protein Design
  - Structure Prediction
  - Machine Learning
  - Jobs
  - Workflows
  properties:
  - type: OpenAPI
    url: openapi/dyno-phi-openapi.yml
  - type: Documentation
    url: https://design.dynotx.com/docs
  - type: APIReference
    url: https://api.dyno-agents.app/
  - type: Authentication
    url: authentication/dyno-authentication.yml
  - type: Conventions
    url: conventions/dyno-conventions.yml
  - type: ErrorCatalog
    url: errors/dyno-problem-types.yml
  - type: DataModel
    url: data-model/dyno-data-model.yml
  - type: RateLimits
    url: rate-limits/dyno-rate-limits.yml
  - type: Overlay
    url: overlays/dyno-phi-overlay.yaml
  - type: Sandbox
    url: sandbox/dyno-sandbox.yml
  - type: CLI
    url: cli/dyno-cli.yml
  - type: AgentSkill
    url: skills/_index.yml
  - type: SDKs
    url: packages/dyno-packages.yml
common:
- type: MCPServer
  url: mcp/dyno-mcp.yml
- type: License
  name: MIT
  url: https://github.com/dynotx/phi-cli/blob/main/LICENSE
- type: Website
  url: https://www.dynotx.com
- type: DeveloperPortal
  url: https://design.dynotx.com/
- type: Documentation
  url: https://design.dynotx.com/docs
- type: APIReference
  url: https://api.dyno-agents.app/
- type: GettingStarted
  url: https://design.dynotx.com/cli
- type: Blog
  url: https://dynotx.substack.com/
- type: GitHubOrganization
  url: https://github.com/dynotx
- type: Support
  url: https://github.com/dynotx/phi-cli/issues
- type: SignUp
  url: https://design.dynotx.com/
- type: TermsOfService
  url: https://www.dynotx.com/legal/terms-and-conditions
- type: PrivacyPolicy
  url: https://www.dynotx.com/legal/privacy-policy
- type: AcceptableUsePolicy
  url: https://design.dynotx.com/acceptable-use
- type: OpenSourceNotice
  url: https://design.dynotx.com/open-source
- type: SourceCode
  url: https://github.com/dynotx/phi-cli
- type: Packages
  url: packages/dyno-packages.yml
- type: SDKs
  url: packages/dyno-packages.yml
- type: CLI
  url: cli/dyno-cli.yml
- type: AgentSkill
  url: skills/_index.yml
- type: Authentication
  url: authentication/dyno-authentication.yml
- type: Conventions
  url: conventions/dyno-conventions.yml
- type: ErrorCatalog
  url: errors/dyno-problem-types.yml
- type: RateLimits
  url: rate-limits/dyno-rate-limits.yml
- type: Plans
  url: plans/dyno-plans-pricing.yml
- type: DataModel
  url: data-model/dyno-data-model.yml
- type: Lifecycle
  url: lifecycle/dyno-lifecycle.yml
- type: ChangeLog
  url: changelog/dyno-changelog.yml
- type: Conformance
  url: conformance/dyno-conformance.yml
- type: Sandbox
  url: sandbox/dyno-sandbox.yml
- type: LLMsTxt
  url: llms/dyno-llms.txt
- type: DomainSecurity
  url: security/dyno-domain-security.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-08-10'
  status: enriched
  artifacts_added: 21
  pass: local-v1
  note: STEP 0b contract discovery overturned the prior "no public developer API" profile. A live OpenAPI 3.1.0 (64 paths,
    80 operations, 62 schemas) is served at https://api.dyno-agents.app/v1/phi/openapi.json with ReDoc at the API root — neither
    the docs host nor the API host answers /openapi.json, so only probing the versioned path prefix found it.