How do I ensure the candidate data is up to date?

The Firefish MCP server fetches data directly from your live Firefish environment. Use the 'getCandidate' tool to retrieve the most recent profile information for any specific candidate ID.

Can I filter jobs by their current status?

Yes! The 'listJobs' tool retrieves all active jobs. You can then ask your AI agent to sort or filter these results based on status, title, or hiring company.

What format should I use for creating a new candidate?

Use the 'createCandidate' tool by providing the first name, last name, and email address. The agent will handle the underlying API request to ensure the record is created correctly in Firefish.

Firefish MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Firefish
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Firefish through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Firefish "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Firefish?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Firefish MCP Server

Connect your Firefish account to any AI agent and automate your recruitment workflows through the Model Context Protocol (MCP). Firefish is a high-performance recruitment CRM that empowers agencies to reach more candidates and close more placements. Now, you can interact with your recruitment data directly through natural conversation.

Pydantic AI validates every Firefish tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Candidate Management — List all candidates, fetch detailed profiles, and create new candidate records instantly.
Job Tracking — Monitor active job vacancies and retrieve complete metadata for any job in your system.
Company & Contact Insights — Access your database of client companies and contacts to stay informed before meetings or calls.
Placement Monitoring — Keep track of successful job placements and recruitment progress across your team.
Advertising Overview — List active job advertisements to see where your recruitment efforts are focused.
Activity Actions — Retrieve a list of recent recruiter actions to maintain a clear audit trail of engagement.
Seamless Integration — Securely connect your Firefish environment using your Client ID and Secret for an automated experience.

The Firefish MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Firefish to Pydantic AI via MCP

Follow these steps to integrate the Firefish MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Firefish with type-safe schemas

Why Use Pydantic AI with the Firefish MCP Server

Pydantic AI provides unique advantages when paired with Firefish through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Firefish integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Firefish connection logic from agent behavior for testable, maintainable code

Firefish + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Firefish MCP Server delivers measurable value.

Type-safe data pipelines: query Firefish with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Firefish tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Firefish and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Firefish responses and write comprehensive agent tests

Firefish MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Firefish to Pydantic AI via MCP:

create_candidate

Create a new candidate

get_candidate

Get candidate details

get_company

Get company details

get_contact

Get contact details

get_job

Get job details

list_actions

List actions

list_adverts

List job adverts

list_candidates

List candidates

list_companies

List companies

list_contacts

List contacts

list_jobs

List jobs

list_placements

List placements

Example Prompts for Firefish in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Firefish immediately.

"List all active job vacancies at Firefish."

"Search for a candidate named 'John Smith'."

"Show me the most recent recruiter actions."

Troubleshooting Firefish MCP Server with Pydantic AI

Common issues when connecting Firefish to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Firefish + Pydantic AI FAQ

Common questions about integrating Firefish MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Firefish MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.