MCP: your team’s assistant, on your own records.

Find candidates, build shortlists and follow up from one conversation. Connect your agency’s AI assistant to the Talisman records your team already works on.

Book a demo See what it costs

Illustration

an assistant, connected to Talisman

An assistant chat window. Somebody asks for qualified accountants in Leeds who are open to a permanent move on up to 55k. A Talisman tool call runs, and three candidate records come back with reference codes, qualifications, towns, availability dates and match scores, above a button reading Add all three to the shortlist.

An illustration of the kind of request. The assistant asks Talisman, and that consultant’s own candidate records come back.

The week this is about

Your team already works this way

Somebody on your desk is using ChatGPT today.

They paste in the CV. They paste in the job spec. The answer lands in a chat window and stops there.

Put the answer to work: search your database, build a shortlist or run a report without leaving the conversation. MCP connects your assistant to Talisman.

We tailor the workflow during onboarding, from adding a CV to following up with a candidate. Your team gives feedback during training, then automates the agreed steps.

An assistant chat window. Somebody attaches a CV and asks for the candidate to be added to Talisman for a Quantity Surveyor role in Bristol with a four week notice period. A Talisman tool call runs, and the new candidate record comes back with a reference code, the role sought, location, notice, mobile number, source, who added it, salary sought and qualification, plus chips reading CV on file, Linked to job and Compliance check started. — An illustrative CV-to-candidate workflow, tailored to your agency during onboarding.

On a perm, contract or temp desk

Ask in your own words, against your own records

What somebody asks	What comes back
Three drivers free on Thursday, cleared for that site	A shortlist with availability and the checks on each worker, waiting for the consultant’s yes
What has happened on this client since March	A summary with the dates, the jobs and the people named in it
Draft the message to every worker whose DBS expires next month	A draft per worker, in the wording you approved, each one waiting for a send
Which of my perm roles is sitting at offer, and for how long	The candidate, the client and the day it reached offer, in one list
Which of my jobs still has a shift open for tomorrow	The open shifts, the client and the hours, in one list

How it actually works

One question, from the chat window to the record

Your consultant

Their assistant

Talisman

Your consultantAsks for the shortlistIn the assistant they already use
Their assistantCalls Talisman as that consultantStraight to the live recordsChatGPT or Claude
TalismanThe sign-in behind itChecked on every call
TalismanAnswers with what they may openThat desk’s candidates, jobs and bookings
Your consultantChecks the proposed actionUsing the assistant’s confirmation settings
TalismanRuns the permitted toolOn the record, in their name

A training-period example. Once feedback is incorporated and your team is confident, automate the agreed workflow.

How far one ask goes

One ask, 100 candidates

Start with a small sample before widening the request.

A consultant asks for an email to all 100 candidates on a job. In their voice. Asking each one whether the role interests them, and asking for an updated CV.

Each draft draws on the candidate’s own record. Use the training period to get the tone and details right, then automate follow-up within your agreed consent rules.

We configure how replies and updated CVs return to the record during onboarding.

An assistant chat window. Somebody asks for an email to all 100 candidates on a job, written in their voice, asking whether they are interested and asking for an updated CV. A Talisman tool call runs and reports 100 drafted, and two example drafts come back, each personalised from the candidate's own record — one citing a conversation in March, the other a forklift ticket valid to April 2027 — above a line reading 100 drafts waiting for you to check. — An illustration of the kind of request. One ask, 100 drafts, each one written from that candidate’s own record.

Connecting it

How you connect it

One sign-in, in the assistant your agency already uses.

You add Talisman as a connector and authorise it once, in your browser. From then on it runs as you, with your permissions.

Agree which tools it may use, including any that send messages or change records.

ChatGPT, Microsoft Copilot and Claude, where your agency has approved them.
Any client that speaks MCP, including the agent frameworks your team tries.
The same Talisman records behind whichever assistant you settle on.

What the connection carries

The person who authorised it, by name
That person’s permissions, on every call
The records that person may open
The supported tools enabled for that connection

MCP access is included in the Talisman Platform, across the modules you have switched on.

How Talisman handles permissions, audit, consent and GDPR

Questions we get asked

MCP FAQ

What can the assistant see?

The connection identifies the authorised user and agency. Available records and actions depend on the supported tools, access controls and modules enabled for that connection.

Where do the records live?

In Talisman. The assistant works the live candidate, contact, client, job and booking records your team already keeps. So the answer comes back with the job number, the worker and the date on it.

Can we write our own agents against it?

Yes. Your developers can use the supported MCP tools from their own agents, with an authorised connection and the access controls configured for it.

How do we know what it did?

During the training period, review tool calls and results, then incorporate feedback. Automate the agreed workflow once your team is confident. Write tools can act directly, so agree permissions and confirmation settings before use.

Compliance

Business Development

Sourcing

Daily Briefings

Timesheets

Point an assistant at your own records

The session runs on your own desks, with an assistant signed in as a named user.

Book a demo