LinkedIn MCP Setup Kit
A folder you can wire an assistant to LinkedIn from, with the exposure of each route stated before the first run rather than after it. Every route from an assistant into LinkedIn in one folder: the maintainers’ own config blocks, the credential each asks for, the exposure each carries and how that exposure was derived, what the sanctioned API cannot do whatever is built on it, and which vendor tools ship an MCP server of their own. Generated from the two directories on this site, so it carries their verification dates rather than a copy of them.
No form on this button. The email form further down exists so we can tell you when the numbers change, not to stand in front of the file.
The folder
linkedin-mcp-kit/
├── README.md # setup, in order
├── LINKEDIN-LIMITS.md
├── ICP.md
├── PRODUCT.md
├── RESEARCH.md
└── PROMPTS/
├── prospect-research.md
├── account-research.md
└── lead-qualification.mdLinkedIn Prospect Research, worked
What this pack produces once the files above are filled in — the actual example from this prompt's own page.
Prospect: Dana Whitfield, Group Finance Director at Northbeam Logistics (~900 staff, 5 countries). Pasted: About section, current role, one post from last week about a five-week close after an acquisition. Seller: founder at Cadence.
Value hypothesis — Dana's close is long because the acquisition added a fifth entity to a process built for four, not because her team is slow; Cadence removes the manual inter-entity reconciliation that grows with each entity. Confidence: high — rests on her own post describing a five-week close "since the acquisition".
Why this might be wrong — She describes the problem as temporary ("since the acquisition"), which suggests she may be waiting for it to settle rather than shopping. If the acquisition closed more than two quarters ago, the window has probably passed.
Opening message — "Dana — your post on the five-week close after the acquisition. The bit I keep seeing: entity count, not team size, is what sets close length. Curious whether the fifth entity added days to reconciliation specifically, or across the board?" (243 characters)
About twenty minutes, most of it writing down your ICP
- Download and unzip. The README and LINKEDIN-LIMITS.md need no editing.
- Read “The routes” and decide which credential you are willing to hand over.
- Copy your server’s block into the file your client reads.
- Attach LINKEDIN-LIMITS.md to the same assistant before the first run.
- Fill ICP.md and PRODUCT.md only if you want the prompts as well. The wiring half needs neither.
What you do with it once it is set up
- Route — Pick the credential class first. It fixes both what the assistant can reach and what the account carries.
- Server — Read the exposure line and the risk paragraph, then copy the block its maintainer publishes.
- Client — Put the block under the key your client actually reads. The keys differ between clients and a wrong one fails silently.
- Limits — Attach LINKEDIN-LIMITS.md to the same assistant. A read tool returning thousands of rows does not raise what one account may contact in a week.
- Work — Run the prompts against what the read tools return: one profile, one company, one list of search results.
- Re-check — Both directories print the day they were read. Re-download when a figure moves rather than trusting the copy on your disk.
Every file, in full, on this site
Nothing in the pack is hidden behind the download. If you would rather take three files than fifteen, take three.
- Context file
LINKEDIN-LIMITS.md
Your assistant stops proposing 300 connection requests a week, because it now knows the ceiling is about 100.
- Context file
ICP.md
Every prompt you run afterwards knows who you sell to, in terms LinkedIn can filter on.
- Context file
PRODUCT.md
Messages stop describing features and start describing what changes for the person receiving them.
- Context file
RESEARCH.md
Research that is consistent between people and between runs, with the evidence line drawn in the same place every time.
- Prompt
LinkedIn Prospect Research
A one-page research brief on a single prospect that ends in a usable opening line, and that separates what it read from what it inferred.
- Prompt
Account Research Brief
An account brief that names the committee, picks the entry point and states one testable hypothesis — built only from what is visible on LinkedIn.
- Prompt
Lead List Qualifier
Your list, split into three tiers with a one-line reason per row, sized to what a LinkedIn account can actually contact in a week.
Get it, and be told when it changes
The zip arrives immediately. The reason to give an address is the second half: LinkedIn moved the Sales Navigator prices in August 2026 and most of the web still quotes the old ones. We will tell you when the figures these files carry stop being current.
Use it for your work and your clients' work
Use every prompt, file and pack for your own company or for clients you are paid by, commercially, modified as much as you like. Put them in your Claude Project, your ChatGPT Project, your Cursor workspace or your agent repo. Share a filled-in copy with your team.
Keep the attribution line at the bottom of any file you redistribute unchanged, and credit Linkediz with a link wherever you republish a resource in full.
Repackage the library or a pack as your own product, paid or free, or scrape the section to rebuild it elsewhere. The downloads exist so you do not have to.
These are writing and research aids. They do not know your customers, they can be wrong, and an assistant will state a fabricated fact as confidently as a true one. Read what comes out before you send it to a person.
Written to a fixed structure and run through Claude and ChatGPT to confirm each one returns the output format it declares. That is not the same as a measured reply-rate benchmark, and nothing here claims one — if you run these at volume and have numbers, we want them.
About this pack
Is this telling me to automate my LinkedIn account?
No. Each entry records what a route is and what it exposes, including the clause in the User Agreement that most of these servers run into. Which route you take, and whether you take one at all, is yours to decide — the kit exists so that it is decided with the whole picture rather than half of it.
Are the configuration blocks yours or the maintainers’?
The maintainers’ own, printed whole. None is composed here, tidied or merged. The client key differs between Claude, VS Code, Zed and Gemini CLI, and a block edited into the wrong shape fails silently rather than erroring — so each one is the block its author tested, with the file its own documentation names.
Why an email, when everything in it is on the site?
Because the file is not the part worth having. Every line of it is rendered on /mcp and /ai/tools with no form in front of it, and the download link works without one. The email buys being told when a figure moves: a repository going quiet, a vendor repricing, LinkedIn changing an allowance.
The reference behind this pack
Every entry in the README is a record on that page, with the sources it was read from.
The kit summarises one price tier per vendor. That directory has the full lists, dated.
What a wired account may actually do, per plan, with the date each figure was read.