linkedin-relay-mcp 3.12.1 → 3.14.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude/skills/linkedin-relay/SKILL.md +124 -19
- package/README.md +51 -4
- package/dist/cli.js +1947 -619
- package/dist/cli.js.map +1 -1
- package/dist/index.js +30 -3
- package/dist/index.js.map +1 -1
- package/dist/mcp-shim.js +1887 -564
- package/dist/mcp-shim.js.map +1 -1
- package/package.json +1 -1
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: linkedin-relay
|
|
3
|
-
description: Research LinkedIn from the user's own account —
|
|
3
|
+
description: Research LinkedIn from the user's own account — find people by company, past company, school, place, title, degree or whose connections they are, search posts, companies, groups, events, courses, products, services and schools, hunt jobs with every filter LinkedIn has and collect their apply links, read profiles, read the chronological feed — and, through the lnrelay CLI, post (text, image or video), comment, reply, react, delete and edit the user's own profile (headline, About, roles, skills) under the approval mode the owner chose. Use when finding or evaluating people (who works or worked somewhere, alumni, people in a role or a city, someone's connections), companies, groups, events, courses, posts on a topic, roles or job openings on LinkedIn, when the user wants job listings or application links, when reading what the user's network is posting, or when the user asks to post, engage or update their profile on LinkedIn. Not for messaging, connection requests or applying to jobs, which do not exist.
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# linkedin-relay
|
|
@@ -30,8 +30,10 @@ in the request path.
|
|
|
30
30
|
## The funnel
|
|
31
31
|
|
|
32
32
|
```
|
|
33
|
-
|
|
34
|
-
|
|
33
|
+
people 1 call / 50 — find people with filters (company, school, place, degree, …)
|
|
34
|
+
jobs 1 call / 100 — find jobs with filters; `job` reads finalists, 100 a call
|
|
35
|
+
search 1 call / 50 — posts, companies, groups, events, courses, products, services, schools
|
|
36
|
+
↓ pick 2-3 finalists from the rows alone, not by reading each one
|
|
35
37
|
profile mid — deep-read ONLY the finalists
|
|
36
38
|
feed mid — what the user's network is posting right now
|
|
37
39
|
↓ feed rows carry likes/comments counts — rank on those before reading a thread
|
|
@@ -41,9 +43,50 @@ whoami cheap — who we are authenticated as
|
|
|
41
43
|
risk / budget free — check standing BEFORE spending
|
|
42
44
|
```
|
|
43
45
|
|
|
44
|
-
|
|
46
|
+
People and search rows already carry name, headline, location and URL. **Rank on those.** Calling `profile` on
|
|
45
47
|
every search result is how a day's budget disappears in one request.
|
|
46
48
|
|
|
49
|
+
## Finding people — the recipe
|
|
50
|
+
|
|
51
|
+
`people` is the people search with every filter LinkedIn has. Each call moves 50 people; a company
|
|
52
|
+
or school given by name costs one extra call to look up.
|
|
53
|
+
|
|
54
|
+
```
|
|
55
|
+
1. people_filters (optional, 1 call) ids and live counts for places, companies, schools,
|
|
56
|
+
industries, services — for this query
|
|
57
|
+
2. people ALL keyword sets in ONE call, the filters, compact:true
|
|
58
|
+
3. rank on headline, location, degree, insight — from the rows alone
|
|
59
|
+
4. profile ONLY the 2-3 finalists, if the row is not enough
|
|
60
|
+
```
|
|
61
|
+
|
|
62
|
+
A worked call, the shape to copy:
|
|
63
|
+
|
|
64
|
+
```
|
|
65
|
+
people keywords:["engineering manager", "head of engineering"] company:["Microsoft"]
|
|
66
|
+
location:"Hungary" network:["2nd"] limit:100 compact:true
|
|
67
|
+
```
|
|
68
|
+
|
|
69
|
+
From a shell: `lnrelay people "engineering manager" "head of engineering" --company Microsoft
|
|
70
|
+
--location Hungary --network 2nd --limit 100 --compact`.
|
|
71
|
+
|
|
72
|
+
- **Check `data.resolved`.** Company and school names, and `location`, are looked up to ids, and the
|
|
73
|
+
choice is reported there. A name can land on a different organisation ("Microsoft Cloud", a
|
|
74
|
+
similarly named school); if it did, re-run with the id from `people_filters` or the row it shows.
|
|
75
|
+
- **Ask the question with filters, not keywords.** "Who works at X" is `company`, not keywords;
|
|
76
|
+
"alumni of Y" is `school`; "in Z" is `location`; "people I can get an intro to" is `network:["2nd"]`;
|
|
77
|
+
"who does A know" is `connectionOf` with A's `id`. Keywords match anywhere on a profile.
|
|
78
|
+
- **`title` is free text against the current title**; `companyText`/`schoolText` are free text too,
|
|
79
|
+
for when there is no single organisation to name.
|
|
80
|
+
- **Budget:** people searches and name lookups spend the general search budget, 25 calls a day.
|
|
81
|
+
A deep query of 1000 people is 20 of them, so ask for the depth you need (`limit`), not the most
|
|
82
|
+
LinkedIn serves; check `budget` before a big run.
|
|
83
|
+
- **LinkedIn pages at most 1000 people per query.** `meta.servedLimit` means it claimed more: split
|
|
84
|
+
the query (by location, by company) rather than reporting the 1000 as everyone.
|
|
85
|
+
- **Not everyone is named.** LinkedIn may return people outside the user's network as
|
|
86
|
+
`"LinkedIn Member"` with no `url`. That is LinkedIn withholding them from this account; count them,
|
|
87
|
+
do not drop them silently, and say so.
|
|
88
|
+
- A row's `id` is the profile id: it goes into `connectionOf` / `followerOf`, and `profile` takes it.
|
|
89
|
+
|
|
47
90
|
## Job hunting — the recipe
|
|
48
91
|
|
|
49
92
|
Jobs have their own commands, their own budget (150 job searches, 60 job reads a day) and their own
|
|
@@ -88,18 +131,79 @@ and `lnrelay job 4479248573 4475225930 4476083905`.
|
|
|
88
131
|
|
|
89
132
|
## Commands
|
|
90
133
|
|
|
91
|
-
### `search` —
|
|
92
|
-
```
|
|
93
|
-
search kind:
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
134
|
+
### `search` — everything else in the search box: posts, companies, groups, events, courses, products, services, schools
|
|
135
|
+
```
|
|
136
|
+
search kind:posts|companies|groups|events|courses|products|services|schools
|
|
137
|
+
keywords:"<terms>" | ["<terms>", …] [filter:["key=v1,v2"]] [limit:N per keyword set] [start:N] [compact]
|
|
138
|
+
companies, services: [location:"<place>"] [network:[1st|2nd|3rd+]] companies: [industry:[ids]]
|
|
139
|
+
posts: [sort:recent|relevant] [posted:24h|week|month] [type:[videos|images|jobs|live|articles|documents]]
|
|
140
|
+
[postedBy:[1st|me]] [from:[profile ids]] [mentions:[profile ids]] [fromCompany:["<name|id>"]]
|
|
141
|
+
[mentionsCompany:["<name|id>"]] [authorCompany:["<name|id>"]] [authorIndustry:[ids]] [authorTitle:"<text>"]
|
|
142
|
+
```
|
|
143
|
+
CLI: `lnrelay search <kind> "<terms>" ["<more>" …] [flags]`; `lnrelay search people|jobs …` hands over to
|
|
144
|
+
`people` and `jobs` with all their flags. One call returns 50 results (posts: 20); several keyword
|
|
145
|
+
sets merge by id, with `matched`, as for `people`.
|
|
146
|
+
|
|
147
|
+
Rows other than posts are `id`, `name`, `subtitle`, `detail`, `summary`, `url`, in LinkedIn's own
|
|
148
|
+
lines; what each line holds depends on the kind:
|
|
149
|
+
|
|
150
|
+
| kind | `subtitle` | `detail` | `id` |
|
|
151
|
+
|---|---|---|---|
|
|
152
|
+
| companies | industry • HQ | followers | company id (`people company:[id]` takes it) |
|
|
153
|
+
| groups | members | — | group id |
|
|
154
|
+
| events | when | where • organiser | event id |
|
|
155
|
+
| courses | length | instructor • released | course id |
|
|
156
|
+
| products | category by vendor | — | product page id |
|
|
157
|
+
| services | the provider's headline | place | the provider's profile id |
|
|
158
|
+
| schools | place | students and alumni | school id (`people school:[id]` takes it) |
|
|
159
|
+
|
|
160
|
+
**Posts** rows: `id` (the post's urn — `post` reads its comments), `url`, `author`, `authorHeadline`
|
|
161
|
+
(people only), `authorUrl` (a profile or a company page), `posted` (as LinkedIn shows it, in the user's
|
|
162
|
+
LinkedIn language: "5h", or "5 órája" in Hungarian), `text`, `reactions`, `comments`, `reposts`.
|
|
163
|
+
- Every `search` call, name lookup included, spends the general search budget (25 a day, shared
|
|
164
|
+
with `people`); ask for the depth you need.
|
|
165
|
+
- A posts call is heavy (about half a megabyte a post on LinkedIn's side), so ask for the depth you
|
|
166
|
+
need. Posts come in LinkedIn's ranking unless `sort:"recent"`.
|
|
167
|
+
- `fromCompany` is the company's own posts; `authorCompany` is posts by people who work there.
|
|
168
|
+
- A group post may come back with no author or counts: LinkedIn keys those differently.
|
|
169
|
+
- Most other filters for a kind (company size, course level, product category, …) go in raw
|
|
170
|
+
`filter`, with the keys and ids `search_filters` lists for that kind.
|
|
171
|
+
|
|
172
|
+
### `search-filters` — 1 search call. A kind's knobs, with ids.
|
|
173
|
+
```
|
|
174
|
+
search_filters kind:companies|groups|events|courses|products|services|schools [keywords] [location]
|
|
175
|
+
```
|
|
176
|
+
Every filter that kind has for the query, with option ids and live counts. Companies, for example:
|
|
177
|
+
`companyHqGeo`, `industryCompanyVertical`, `companySize` (B = 1-10 employees … ), `hasJobs`, `network`.
|
|
178
|
+
Groups, events and schools have none.
|
|
179
|
+
|
|
180
|
+
### `people` — 1 search call per 50 people. People search with every filter.
|
|
181
|
+
```
|
|
182
|
+
people [keywords:"<terms>" | ["<terms>", …]] [company:["<name|id>"]] [pastCompany:["<name|id>"]]
|
|
183
|
+
[school:["<name|id>"]] [location:"<place>" | geo:["<id>"]] [network:[1st|2nd|3rd+]]
|
|
184
|
+
[industry:[ids]] [language:["en"]] [service:[ids]] [title:"<text>"] [firstName] [lastName]
|
|
185
|
+
[companyText] [schoolText] [connectionOf:"<id>"] [followerOf:"<id>"] [openToVolunteer]
|
|
186
|
+
[filter:["key=v1,v2"]] [limit:1-1000 per keyword set] [start:N] [compact]
|
|
187
|
+
```
|
|
188
|
+
CLI: `lnrelay people "<terms>" ["<more>" …] [--company "<name|id>" …] [--location "<place>"]
|
|
189
|
+
[--network 2nd] [--title "<text>"] [--limit N] [--compact]` — every option is in `lnrelay help`.
|
|
190
|
+
Company, past company and school take names or ids; repeat the flag for several names (a name may
|
|
191
|
+
contain commas), or comma-separate ids.
|
|
192
|
+
|
|
193
|
+
Each item: `id`, `name`, `headline`, `location`, `degree` (`1st`, `2nd`, `3rd+`, `out of network`),
|
|
194
|
+
`verified`, `insight` (mutual connections, followers, services offered), `url`, and `matched` with
|
|
195
|
+
several keyword sets. `compact` gives one line per person. `data.resolved` lists each name and the
|
|
196
|
+
id it became. Paging and `meta` work as for `jobs`, plus `meta.servedLimit` when LinkedIn claimed
|
|
197
|
+
more people than the 1000 it serves. Filters alone are a search: `connectionOf` with no keywords
|
|
198
|
+
lists that person's connections.
|
|
199
|
+
|
|
200
|
+
### `people-filters` — 1 search call. The knobs, with ids.
|
|
201
|
+
```
|
|
202
|
+
people_filters [keywords:"<terms>"] [any people filter]
|
|
203
|
+
```
|
|
204
|
+
Every people filter for the query: its key, whether it takes ids or free text, and its options'
|
|
205
|
+
`value`, `label` and live `count`. The ids go into `geo`, `industry`, `service`, `company`, … or raw
|
|
206
|
+
`filter:["<key>=<value>"]`.
|
|
103
207
|
|
|
104
208
|
### `jobs` — 1 job-search call per 100 results. Job search with every filter.
|
|
105
209
|
```
|
|
@@ -282,9 +386,10 @@ Every collection carries:
|
|
|
282
386
|
|---|---|
|
|
283
387
|
| `state: complete` | every reference resolved; an empty `items` here genuinely means none |
|
|
284
388
|
| `state: partial` | **some references failed to resolve** — the record is incomplete, not small |
|
|
285
|
-
| `state: unknown` | we stopped at the limit and cannot prove exhaustion (
|
|
286
|
-
| `next` | `jobs`: the `start` that continues this search; absent when the results ran out |
|
|
287
|
-
| `
|
|
389
|
+
| `state: unknown` | we stopped at the limit and cannot prove exhaustion (`post`, `reactions`, `feed`) |
|
|
390
|
+
| `next` | `jobs` / `people` / `search`: the `start` that continues this search; absent when the results ran out |
|
|
391
|
+
| `servedLimit` | `people` / `search`: LinkedIn claimed more matches than it serves (1000 a query) — the list is NOT everyone; narrow the query |
|
|
392
|
+
| `searches` / `duplicates` | `jobs` / `people` / `search` with several keyword sets: each set's own count and state, and how many repeats were merged |
|
|
288
393
|
| `unread` | `jobs --details` / `job`: jobs LinkedIn did not return in full — they are not closed, just unread |
|
|
289
394
|
| `returnedCount` vs `claimedCount` | `claimed > 0` with `returned === 0` is a **failed fetch**, never "no results" |
|
|
290
395
|
| `excludedCount` | ads and UI chrome deliberately dropped |
|
package/README.md
CHANGED
|
@@ -9,7 +9,10 @@ Sibling to [`x-relay`](../x-relay), [`github-relay`](../github-relay) and
|
|
|
9
9
|
```bash
|
|
10
10
|
npm i -g linkedin-relay-mcp
|
|
11
11
|
lnrelay login # mint a session from your own Chrome
|
|
12
|
-
lnrelay
|
|
12
|
+
lnrelay people "engineering manager" --company Microsoft --location Hungary --compact
|
|
13
|
+
# people search with every filter, names looked up
|
|
14
|
+
lnrelay search posts "AI agents" --posted week --sort recent --compact
|
|
15
|
+
# posts, companies, groups, events, courses, products, …
|
|
13
16
|
lnrelay jobs "frontend engineer" "AI agent developer" --workplace remote --posted week --compact
|
|
14
17
|
# one merged job list across keyword sets
|
|
15
18
|
lnrelay job 4479248573 4475225930 # full jobs, with their apply links
|
|
@@ -21,9 +24,10 @@ lnrelay local "rust" # then search it offline, free
|
|
|
21
24
|
|
|
22
25
|
## As an MCP server
|
|
23
26
|
|
|
24
|
-
|
|
27
|
+
Twenty-two read-only tools, so an agent does the reading. Writes are not on that surface at any price.
|
|
25
28
|
The bundled Claude Code skill (`.claude/skills/linkedin-relay/SKILL.md`) teaches an agent the
|
|
26
|
-
funnels, the budget, and how to read `meta` — including
|
|
29
|
+
funnels, the budget, and how to read `meta` — including step-by-step recipes for finding people and
|
|
30
|
+
for job hunting.
|
|
27
31
|
|
|
28
32
|
```bash
|
|
29
33
|
claude mcp add linkedin-relay -s user -- bun "$(npm root -g)/linkedin-relay-mcp/dist/mcp-shim.js"
|
|
@@ -33,7 +37,9 @@ claude mcp add linkedin-relay -s user -- bun "$(npm root -g)/linkedin-relay-mcp/
|
|
|
33
37
|
|
|
34
38
|
| | |
|
|
35
39
|
|---|---|
|
|
36
|
-
| `
|
|
40
|
+
| `people` · `people-filters` | people search with every filter: company, past company, school, place, degree, title, someone's connections |
|
|
41
|
+
| `search` · `search-filters` | posts, companies, groups, events, courses, products, services, schools — each with its filters |
|
|
42
|
+
| `profile` · `feed` | a profile, your feed |
|
|
37
43
|
| `jobs` · `job` · `job-filters` | job search with every filter, several keyword sets merged in one call, and apply links |
|
|
38
44
|
| `post` · `reactions` | a post's comment thread, and who engaged |
|
|
39
45
|
| `scheduled` · `experience` · `skills` | your queued posts, and your own roles and skills |
|
|
@@ -77,6 +83,47 @@ approved the way **you** chose with `lnrelay approval set` (only at a real termi
|
|
|
77
83
|
There is no `--yes` and no environment variable. Every approval and outcome is logged to
|
|
78
84
|
`~/.lnrelay/writes.jsonl`.
|
|
79
85
|
|
|
86
|
+
## Searching everything else
|
|
87
|
+
|
|
88
|
+
`lnrelay search <kind>` covers the rest of the search box — `posts`, `companies`, `groups`, `events`,
|
|
89
|
+
`courses`, `products`, `services`, `schools` — and hands `people` and `jobs` to their own commands.
|
|
90
|
+
|
|
91
|
+
```bash
|
|
92
|
+
lnrelay search posts "AI agents" --posted week --author-company Microsoft --compact
|
|
93
|
+
lnrelay search companies "fintech" --location Hungary --filter companySize=C,D --compact
|
|
94
|
+
lnrelay search courses "python" --filter difficultyLevel=Beginner
|
|
95
|
+
lnrelay search-filters companies "fintech" # every filter for a kind, ids and counts
|
|
96
|
+
```
|
|
97
|
+
|
|
98
|
+
- **Posts** come with author, time, text and reaction, comment and repost counts, filterable by date,
|
|
99
|
+
type, author, author's company, industry and title, and mentions. LinkedIn serves them over a
|
|
100
|
+
heavier interface than the rest, 20 a call.
|
|
101
|
+
- **Everything else** comes back 50 a call as LinkedIn's own lines (a company's industry and HQ and
|
|
102
|
+
followers, an event's time and place, a course's length and instructor), with each kind's filters
|
|
103
|
+
through `--filter key=value` and `search-filters`.
|
|
104
|
+
- Several keyword sets merge by id, as for people and jobs.
|
|
105
|
+
|
|
106
|
+
## Finding people
|
|
107
|
+
|
|
108
|
+
```bash
|
|
109
|
+
lnrelay people "engineering manager" "head of engineering" --company Microsoft --location Hungary --network 2nd --compact
|
|
110
|
+
lnrelay people --school "Budapest University of Technology" --company OTP --limit 200 # alumni at a company
|
|
111
|
+
lnrelay people --connection-of <profile-id> --network 2nd # their connections you are not yet connected to
|
|
112
|
+
lnrelay people-filters "frontend developer" --location Budapest # every filter, ids and counts
|
|
113
|
+
```
|
|
114
|
+
|
|
115
|
+
- **Every filter the people search has:** current and past company, school, place, connection
|
|
116
|
+
degree, industry, profile language, service category, the connections or followers of a person,
|
|
117
|
+
open to volunteering, and free-text first name, last name, title, company and school.
|
|
118
|
+
- **Names, not ids.** `--company`, `--past-company`, `--school` and `--location` take names and look
|
|
119
|
+
them up; `data.resolved` says what each became, so a wrong match is visible.
|
|
120
|
+
- **50 people a call** (the page asks for 10). Asking for 100 is answered with an *empty success*, so
|
|
121
|
+
the tool never does. Several keyword sets merge by person, as for jobs.
|
|
122
|
+
- **LinkedIn serves at most 1000 people per query**, whatever it claims to have matched;
|
|
123
|
+
`meta.servedLimit` says when it held back, and the list is reported partial, not complete.
|
|
124
|
+
- People searches and name lookups spend the general search budget (25 calls a day), so a
|
|
125
|
+
1000-person query takes most of a day's allowance.
|
|
126
|
+
|
|
80
127
|
## Job hunting
|
|
81
128
|
|
|
82
129
|
```bash
|