linkedin-relay-mcp 3.9.0 → 3.10.1
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 +45 -2
- package/dist/cli.js +754 -156
- package/dist/cli.js.map +1 -1
- package/dist/index.js +55 -12
- package/dist/index.js.map +1 -1
- package/dist/mcp-shim.js +702 -87
- package/dist/mcp-shim.js.map +1 -1
- package/package.json +1 -1
|
@@ -12,7 +12,8 @@ in the request path.
|
|
|
12
12
|
## Three things to know before you call anything
|
|
13
13
|
|
|
14
14
|
1. **Every call spends a budget that cannot be topped up.** Caps are deliberately low (30 profile
|
|
15
|
-
reads a day, 25 searches,
|
|
15
|
+
reads a day, 25 searches, 350 requests total; job hunting has its own 150 job searches and 60
|
|
16
|
+
job reads) because LinkedIn restricts accounts for *read*
|
|
16
17
|
velocity alone — several documented restrictions involved no automation and no writes, just fast
|
|
17
18
|
browsing. Check `meta.budget.remaining`; when it's low, tell the user and stop rather than
|
|
18
19
|
spending the rest.
|
|
@@ -47,7 +48,7 @@ every search result is how a day's budget disappears in one request.
|
|
|
47
48
|
|
|
48
49
|
### `search` — cheap. The net.
|
|
49
50
|
```
|
|
50
|
-
search kind:people|companies
|
|
51
|
+
search kind:people|companies query:"<terms>" [limit:1-25] (jobs: use `jobs`)
|
|
51
52
|
```
|
|
52
53
|
Returns `{items, meta}`. Each item: `name`, `headline`, `location`, `url`, `urn`.
|
|
53
54
|
|
|
@@ -58,6 +59,48 @@ Out-of-network people come back as `name: "LinkedIn Member"` with a `/headless`
|
|
|
58
59
|
LinkedIn behaviour, not a bug — LinkedIn will not name them to this account. Say so rather than
|
|
59
60
|
presenting it as a data problem.
|
|
60
61
|
|
|
62
|
+
### `jobs` — 1 job-search call per 25 results. Job search with every filter.
|
|
63
|
+
```
|
|
64
|
+
jobs keywords:"<terms>" [location:"<place>" | geoId:"<id>"] [distance:<miles>]
|
|
65
|
+
[posted:"24h|week|month|<N>h|<N>d"] [experience:[internship|entry|associate|mid-senior|director|executive]]
|
|
66
|
+
[type:[full-time|part-time|contract|temporary|volunteer|internship|other]]
|
|
67
|
+
[workplace:[on-site|remote|hybrid]] [easyApply] [under10] [verified] [inNetwork] [fairChance]
|
|
68
|
+
[company|industry|function|title|place:[ids]] [filter:["key=v1,v2"]] [sort:recent|relevant]
|
|
69
|
+
[limit:1-100] [start:N] [details] [description] [compact]
|
|
70
|
+
```
|
|
71
|
+
Each item: `id`, `title`, `company`, `location`, `workplace`, `listed` (YYYY-MM-DD), `easyApply`,
|
|
72
|
+
`promoted`, `salary` (when the card shows one), `insights`, `url`. `compact` gives one line per job.
|
|
73
|
+
|
|
74
|
+
- **Rank on the rows, then read the finalists with `job`.** `details` reads *every* row (1 profile
|
|
75
|
+
job read each, 60 a day) to add the apply link, applicants and employment type.
|
|
76
|
+
- **Check `data.location`.** A typed location is resolved by LinkedIn, and the place it chose is
|
|
77
|
+
reported there. "Vienna, Austria" resolved to one district of Vienna. Pass `geoId` for an exact
|
|
78
|
+
place; ids are in `job_filters` under `populatedPlace`.
|
|
79
|
+
- **Paging:** `meta.claimedCount` is LinkedIn's total, `meta.next` is the `start` for the next
|
|
80
|
+
batch, and `meta.state` is `complete` only when the results ran out. LinkedIn serves at most 1000
|
|
81
|
+
per search; narrow the query rather than paging deep.
|
|
82
|
+
- Job hunting has its own budget: 150 job-search calls and 60 job reads a day, apart from the
|
|
83
|
+
people and company `search`. That is about ten keyword searches read in full. The same job turns
|
|
84
|
+
up under several keywords; merge the lists by `id` before reading any in full.
|
|
85
|
+
|
|
86
|
+
### `job` — 1 job read. One job, in full.
|
|
87
|
+
```
|
|
88
|
+
job job:"<id | /jobs/view/ URL | ?currentJobId= URL>"
|
|
89
|
+
```
|
|
90
|
+
`description`, `apply: {type: "external" | "easy-apply", url}`, `company`, `companyUrl`,
|
|
91
|
+
`location`, `workplace`, `employmentType`, `experienceLevel`, `industries`, `functions`, `listed`,
|
|
92
|
+
`expires`, `state` (`LISTED` or `CLOSED`), `applicants`, `ats` (the employer's applicant tracking
|
|
93
|
+
system), and `applied` / `saved` for this user. For an external application, `apply.url` goes to
|
|
94
|
+
the employer's own site.
|
|
95
|
+
|
|
96
|
+
### `job-filters` — 1 job-search call. The knobs, with ids.
|
|
97
|
+
```
|
|
98
|
+
job_filters keywords:"<terms>" [location | geoId] [any jobs filter]
|
|
99
|
+
```
|
|
100
|
+
Every filter LinkedIn offers for this query, each with its options' `value`, `label` and live
|
|
101
|
+
`count`. These values go into `company`, `industry`, `function`, `title`, `place`, or raw
|
|
102
|
+
`filter:["<key>=<value>,…"]` for anything else (benefits, commitments, …).
|
|
103
|
+
|
|
61
104
|
### `profile` — mid. Read only the finalists.
|
|
62
105
|
```
|
|
63
106
|
profile id:"<public-id|urn|linkedin.com/in/… URL>"
|