> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# OpenAPI Toolset
> Turn any OpenAPI 3 or Swagger 2 spec into callable agent tools with one import
Point an agent at a REST API's spec and every operation becomes a tool it can call — no per-endpoint wrapper functions, no external MCP process.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "OpenAPI Toolset"
Spec[📋 OpenAPI Spec] --> Toolset[🔌 OpenAPIToolset]
Toolset --> Ops[🧰 List of Operations]
Ops --> Agent[🤖 Agent]
Agent --> HTTP[🌐 HTTP call]
HTTP --> Resp[✅ Response]
end
classDef input fill:#6366F1,stroke:#7C90A0,color:#fff
classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
classDef agent fill:#8B0000,stroke:#7C90A0,color:#fff
classDef result fill:#10B981,stroke:#7C90A0,color:#fff
class Spec input
class Toolset,Ops,HTTP process
class Agent agent
class Resp result
```
## Quick Start
Every operation in the spec becomes a tool the agent can call directly.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
import os
from praisonaiagents import Agent
from praisonaiagents.tools.openapi_toolset import OpenAPIToolset
toolset = OpenAPIToolset(
spec_url="https://api.example.com/openapi.json",
auth={"type": "bearer", "token": os.environ["API_TOKEN"]},
)
agent = Agent(name="ops", tools=toolset.get_tools())
agent.start("List the last 5 incidents and open a ticket for the top one")
```
`httpx` is needed at call time.
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install httpx
```
YAML specs also need `PyYAML` (already a dependency).
***
## How It Works
`get_tools()` returns one callable `OpenAPIOperation` per spec operation. When the agent calls one, it builds the request, attaches auth headers, sends it with `httpx`, and returns the parsed JSON.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant User
participant Agent
participant Operation
participant httpx
participant API
User->>Agent: Request
Agent->>Operation: call(**kwargs)
Operation->>Operation: build_request() + attach auth headers
Operation->>httpx: send request
httpx->>API: HTTP call
API-->>httpx: response
httpx-->>Operation: JSON or text
Note over Operation: Transport failures and safety refusals (off-origin,
scheme downgrade, hostless URL) all come back as
"{name} failed: {reason}" so the model can react
instead of ending the turn
Operation-->>Agent: result
Agent-->>User: Response
```
***
## Loading a Spec
Provide the spec exactly one of three ways — otherwise a `ValueError` is raised.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph TB
Q{How is the spec
available?} -->|Already parsed
dict/YAML loaded| Dict[spec_dict=...]
Q -->|Raw JSON/YAML text| Str[spec_str=...]
Q -->|Hosted at a URL| Url[spec_url=...]
Dict --> Filter{Combining specs
or limiting tools?}
Str --> Filter
Url --> Filter
Filter -->|Keep some operations| TF[tool_filter=...]
Filter -->|Avoid name clashes| TP[tool_name_prefix=...]
classDef q fill:#6366F1,stroke:#7C90A0,color:#fff
classDef opt fill:#189AB4,stroke:#7C90A0,color:#fff
class Q,Filter q
class Dict,Str,Url,TF,TP opt
```
***
## Configuration Options
All constructor arguments are keyword-only.
| Option | Type | Default | Description |
| ------------------ | ------------------------------------------- | -------- | -------------------------------------------------------------------------------------------- |
| `spec_dict` | `Optional[Dict[str, Any]]` | `None` | Parsed spec (JSON/YAML already loaded) |
| `spec_str` | `Optional[str]` | `None` | Raw spec text (JSON or YAML) |
| `spec_url` | `Optional[str]` | `None` | URL of a JSON or YAML spec |
| `base_url` | `Optional[str]` | inferred | Overrides `servers[0].url` / `host+basePath`. Required only when the spec has no server info |
| `auth` | `Optional[Dict[str, Any]]` | `None` | See the auth table below |
| `tool_filter` | `Optional[Callable[[str, str, str], bool]]` | `None` | Called with `(name, method, path)`; return `True` to keep the operation |
| `tool_name_prefix` | `Optional[str]` | `None` | Prepended to every generated tool name |
| `header_provider` | `Optional[Callable[[], Dict[str, str]]]` | `None` | Called per request; adds/overrides headers (use for rotating tokens) |
| `timeout` | `int` | `30` | Per-request timeout, in seconds |
Exactly one of `spec_dict`, `spec_str`, `spec_url` is required.
### Methods
| Method | Returns | Description |
| ------------- | ------------------------ | -------------------------------------------------------- |
| `get_tools()` | `List[OpenAPIOperation]` | One callable per operation, ready for `Agent(tools=...)` |
### OpenAPIOperation
Each tool returned by `get_tools()` is an `OpenAPIOperation`.
| Member | Type | Description |
| ------------------------- | ---------------- | ------------------------------------------------------------------------------ |
| `operation(**kwargs)` | `dict \| str` | Parsed JSON, else response text; on failure returns `"{name} failed: {error}"` |
| `build_request(**kwargs)` | `Dict[str, Any]` | Pure argument-binding (no HTTP) — preview or test the assembled request |
| `to_openai_tool()` | `Dict[str, Any]` | Function-calling dict, via the same helper MCP tools use |
Attributes: `name`, `description`, `method`, `path`, `base_url`, `parameters`, `body_schema`, `body_param`, `input_schema`, `auth`, `header_provider`, `timeout`.
### Auth Shapes
The `auth` dict is keyed by `type`.
| `auth["type"]` | Required keys | Header emitted |
| -------------- | -------------------------------------------- | ------------------------------- |
| `"bearer"` | `token` | `Authorization: Bearer ` |
| `"api_key"` | `key`, optional `name` (default `X-API-Key`) | `: ` |
| `"basic"` | `value` (already base64-encoded `user:pass`) | `Authorization: Basic ` |
***
## Safety Behaviour
The toolset refuses unsafe requests and never fetches arbitrary URLs while parsing.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph TB
Req[📝 Tool call] --> Build[🧠 build_request]
Build --> Host{Same host
as base_url?}
Host -->|No| RefuseHost[⛔ Refuse: off-origin]
Host -->|Yes| Scheme{Same scheme
https vs http?}
Scheme -->|No| RefuseScheme[⛔ Refuse: scheme downgrade]
Scheme -->|Yes| HasHost{Has a host
at all?}
HasHost -->|No| RefuseHostless[⛔ Refuse: pass base_url=]
HasHost -->|Yes| Send[🌐 Send to API]
classDef req fill:#6366F1,stroke:#7C90A0,color:#fff
classDef process fill:#F59E0B,stroke:#7C90A0,color:#fff
classDef refuse fill:#8B0000,stroke:#7C90A0,color:#fff
classDef send fill:#10B981,stroke:#7C90A0,color:#fff
class Req req
class Build,Host,Scheme,HasHost process
class RefuseHost,RefuseScheme,RefuseHostless refuse
class Send send
```
| Behaviour | What happens |
| ----------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **`http://` + auth** | Raises `ValueError` — credentials are never sent in the clear. Pass an `https://` `base_url` or fix the spec |
| **Swagger 2 schemes** | When both `http` and `https` are listed, `https` wins (not `schemes[0]`) |
| **Remote `$ref`** | Ignored — parsing a spec never fetches external URLs. Self-referential schemas are cycle-broken to `{"type": "object"}` |
| **Path parameters** | Every value is `quote(value, safe="")` before substitution, so `../../admin` or `https://other/` cannot alter host, path, query or fragment |
| **Origin pin (host)** | If an absolute path in the spec, or any argument path, would send the request to a host other than the configured `base_url`, the tool returns `"{name} failed: {name}: refusing to send credentialed request to {other_origin}; configured origin is {configured_origin}"`. Credentials never leave the configured origin |
| **Origin pin (scheme)** | A same-host `http://` value in the spec is refused the same way when the configured `base_url` is `https://` — no silent HTTPS→HTTP downgrade |
| **Strict body (OpenAPI 3)** | Only properties declared in the `requestBody` schema are sent — framework-injected kwargs (e.g. `idempotency_key`) are dropped, so `additionalProperties: false` schemas stay clean |
| **Swagger 2 `in: body`** | The whole named argument becomes the JSON body verbatim |
| **Relative `servers[0].url`** | A remotely loaded spec with `servers: [{ url: "/v1" }]` resolves against the `spec_url`. With `spec_dict=` or `spec_str=` there is no URL to resolve against — the tool returns `"{name} failed: {name}: no host to send to -- the spec's server URL is relative ('/v1') and could not be resolved. Pass an absolute base_url= to OpenAPIToolset."` instead of an opaque transport error |
| **Tool names** | `operationId` is sanitised; when absent, name is `method + "_" + sanitised path` — stable across runs |
| **Errors return, not raise** | A network/HTTP failure comes back as `"{name} failed: {exc}"` so the model can react instead of ending the turn. The `ValueError`s raised inside `build_request()` (the two origin/hostless refusals above) are caught by `__call__()` and returned the same way |
| **`header_provider` faults** | If the provider raises, the request continues without its headers (a warning is logged) |
***
## Common Patterns
**Restrict the tool surface to read-only operations:**
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents.tools.openapi_toolset import OpenAPIToolset
toolset = OpenAPIToolset(
spec_url="https://api.example.com/openapi.json",
tool_filter=lambda name, method, path: method.lower() == "get",
)
```
**Namespace a spec when combining several on one agent:**
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
stripe = OpenAPIToolset(
spec_url="https://api.stripe.com/openapi.json",
tool_name_prefix="stripe_",
)
```
**Rotate auth per request:**
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def fetch_token() -> str:
return "..." # your token-refresh logic
toolset = OpenAPIToolset(
spec_url="https://api.example.com/openapi.json",
header_provider=lambda: {"Authorization": f"Bearer {fetch_token()}"},
)
```
**Preview a request without calling the API:**
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
tools = OpenAPIToolset(spec_url="https://api.example.com/openapi.json").get_tools()
request = tools[0].build_request(id="123")
print(request) # {"method": ..., "url": ..., "headers": ...}
```
**Force a base URL when the spec has a relative `servers:` entry:**
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents.tools.openapi_toolset import OpenAPIToolset
toolset = OpenAPIToolset(
spec_dict=my_spec, # servers: [{ url: "/v1" }]
base_url="https://api.example.com", # required — no spec_url to resolve against
auth={"type": "bearer", "token": "..."},
)
```
***
## OpenAPI Toolset vs MCP
Both expose external tools to an agent; reach for the toolset when the API already has a spec.
| | OpenAPI Toolset | MCP OpenAPI server |
| ------------------ | ---------------------------------------------------------------- | ------------------ |
| Extra process | None | `npx` subprocess |
| Language runtime | Python only | Node.js required |
| `tool_filter` | Built in | Not available |
| `tool_name_prefix` | Built in | Not available |
| Agent view | Routes through `build_openai_tool_dict` — identical to MCP tools | Identical |
A workaround existed (`MCP("npx -y @ivotoby/openapi-mcp-server ...")`); the toolset removes the extra process and the npx dependency, and adds first-class `tool_filter` and `tool_name_prefix`.
***
## Best Practices
The toolset refuses to attach credentials to an `http://` endpoint. If the
spec declares a cleartext server, pass an `https://` `base_url` explicitly.
A same-host scheme downgrade — a spec supplying `http://` for an origin you
configured as `https://` — is refused too, so a token never travels in the
clear.
A large spec can generate dozens of tools. Use `tool_filter` to keep only
read-only or task-relevant operations so the model isn't overwhelmed.
Two specs may both define `get_users`. Set a distinct `tool_name_prefix`
per toolset so names stay unique on one agent.
When you point the toolset at a spec URL you do not control, the spec — not
just the model — can try to relocate a call. The toolset pins every
credentialed request to your configured origin's host and scheme, so an
absolute path in the spec cannot silently send your token somewhere else.
Nothing to do — this is on by default; the tool returns a refusal message
the model can see.
`build_request(**args)` binds arguments to URL, headers and body without
any HTTP call — assert the assembled request in a unit test.
***
## Related
Front external tools as an MCP server
Build and register agent tools
Group related tools together
Configure how tools run