io.github.devag7/linkedin-mcp
NPM · LINKEDIN-MCP-TOOLS · SCANNED SEP 20
LinkedIn for AI assistants — search, profiles, jobs, feed, messaging, and gated writes.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 98 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 94 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1406 tokens (~63/item across 22 items; 22 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
- Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage99
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 97% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_message" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 22 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the io.github.devag7/linkedin-mcp server?
io.github.devag7/linkedin-mcp runs locally as an npm package, launched with npx -y linkedin-mcp-tools. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · linkedin-mcp-tools
claude mcp add devag7-linkedin-mcp -- npx -y linkedin-mcp-tools
{
"mcpServers": {
"devag7-linkedin-mcp": {
"command": "npx",
"args": [
"-y",
"linkedin-mcp-tools"
]
}
}
} {
"servers": {
"devag7-linkedin-mcp": {
"command": "npx",
"args": [
"-y",
"linkedin-mcp-tools"
]
}
}
} codex mcp add devag7-linkedin-mcp -- npx -y linkedin-mcp-tools
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"devag7-linkedin-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"linkedin-mcp-tools"
],
"enabled": true
}
}
} openclaw mcp add devag7-linkedin-mcp --command npx --arg -y --arg linkedin-mcp-tools
mcp_servers:
devag7-linkedin-mcp:
command: "npx"
args: ["-y", "linkedin-mcp-tools"] {
"McpServers": {
"devag7-linkedin-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"linkedin-mcp-tools"
]
}
}
} assistant mcp add devag7-linkedin-mcp -t stdio -c npx -a -y linkedin-mcp-tools
{
"mcpServers": {
"devag7-linkedin-mcp": {
"command": "npx",
"args": [
"-y",
"linkedin-mcp-tools"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 −2
- Stability: pass → 0.83 functional
- 16 Sept 26 0
- Stability: 0.97 → pass security
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 −2
- Stability: pass → 0.80 functional
- 9 Sept 26 0
- Stability: 0.97 → pass security
- 8 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed npm/linkedin-mcp-tools@2.0.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 98 packages
| Packages resolved | 98 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
close_session ~21
Close the browser context and release resources (kills the Chrome process).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
comment_on_post ~96
[ALPHA, write] Comment on a post. Gated: requires confirm:true. Returns a structured status.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Must be true to actually execute. Omit/false = refuse (safety). |
| post_urn | string | yes | The post ACTIVITY urn, e.g. urn:li:activity:7472… (not the share urn) |
| text | string | yes | Comment text |
No output schema declared.
No examples provided.
connect_with_person ~117
[ALPHA, write] Send a connection request. Gated: requires confirm:true. Returns a structured status (ok | duplicate | already_connected | restricted | quota_exhausted | failed). Counts against the daily connect cap.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Must be true to actually execute. Omit/false = refuse (safety). |
| message | string | – | Optional note (max 300 chars) |
| profile_id | string | yes | The fsd_profile id (the ACoAA… part of the profile URN) |
No output schema declared.
No examples provided.
create_post ~74
[ALPHA, write] Publish a text post to your feed. Gated: requires confirm:true. Returns a structured status.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Must be true to actually execute. Omit/false = refuse (safety). |
| text | string | yes | Post text |
| visibility | string | – | Audience |
No output schema declared.
No examples provided.
get_company ~58
Get a company by its LinkedIn URL slug (e.g. "google", "microsoft"). Returns name, description, website, industry, size, HQ.
| Name | Type | Req | Description |
|---|---|---|---|
| universal_name | string | yes | Company URL slug, e.g. "google" |
No output schema declared.
No examples provided.
get_company_employees ~76
List employees LinkedIn surfaces for a company (by URL slug). Returns name, headline, and public identifier (feed the slug to get_profile). Prospecting core.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Employees to return (default 10) |
| universal_name | string | yes | Company URL slug, e.g. "anthropicresearch" |
No output schema declared.
No examples provided.
get_company_posts ~67
Get a company's recent posts by its LinkedIn URL slug (e.g. "google"). Returns post text + a short meta line.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Posts to return (default 10) |
| universal_name | string | yes | Company URL slug, e.g. "google" |
No output schema declared.
No examples provided.
get_conversation ~55
Read messages in a LinkedIn conversation by its URN (get the URN from get_inbox).
| Name | Type | Req | Description |
|---|---|---|---|
| conversation_urn | string | yes | Full urn:li:msg_conversation:(...) from a get_inbox result |
No output schema declared.
No examples provided.
get_feed ~37
Get recent posts from your LinkedIn home feed (author + post text).
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Number of posts (default 10) |
No output schema declared.
No examples provided.
get_inbox ~25
List your recent LinkedIn messaging conversations (title, last activity, unread count).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_job_details ~58
Get full details for a job posting by its numeric id (the digits in /jobs/view/<id> or from search_jobs jobUrn).
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | Numeric job id, e.g. "4423697734" |
No output schema declared.
No examples provided.
get_my_profile ~26
Get the authenticated user's own LinkedIn profile (experience, education, headline, summary).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_notifications ~36
Get your recent LinkedIn notifications (headline, time, read state).
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Number of notifications (default 20) |
No output schema declared.
No examples provided.
get_pending_invitations ~68
List your pending connection invitations — received (inbound, with the urn/sharedSecret to accept later) and sent (outbound). Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Max per direction (default 50) |
| direction | string | – | Which queue to return (default both) |
No output schema declared.
No examples provided.
get_profile ~56
Get a LinkedIn profile by public identifier (the slug in the profile URL, e.g. "satyanadella").
| Name | Type | Req | Description |
|---|---|---|---|
| username | string | yes | LinkedIn public identifier / vanity slug, e.g. "williamhgates" |
No output schema declared.
No examples provided.
health_check ~53
Deep health check: cookie login state, a LIVE Voyager probe (confirms the API actually answers, not just that a cookie exists), and today's safety-budget headroom (per-action used/cap/remaining + pending invites).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
react_to_post ~94
[ALPHA, write] React to a post. Gated: requires confirm:true. Returns a structured status.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Must be true to actually execute. Omit/false = refuse (safety). |
| post_urn | string | yes | The post ACTIVITY urn, e.g. urn:li:activity:7472… (not the share urn) |
| reaction | string | – | – |
No output schema declared.
No examples provided.
search_companies ~62
Search LinkedIn companies by keywords. Returns name + universalName slug (pass that to get_company for full details).
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Results (default 10) |
| keywords | string | yes | Search keywords, e.g. "fintech bangalore" |
No output schema declared.
No examples provided.
search_jobs ~76
Search LinkedIn jobs by keywords (and optional location). Returns title, location, posted time.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Results (default 10) |
| keywords | string | yes | Job search keywords, e.g. "software engineer" |
| location_geo_id | string | – | Optional LinkedIn geo URN id to scope the location |
No output schema declared.
No examples provided.
search_people ~66
Search LinkedIn people by keywords. Returns name, headline, location, and public identifier (pass that to get_profile for full details).
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | Results (default 10) |
| keywords | string | yes | Search keywords, e.g. "recruiter at Google" |
No output schema declared.
No examples provided.
send_message ~166
[ALPHA, write] Send a message. Pass thread_id / conversation_urn to REPLY into an existing conversation (verified); otherwise a new thread is started to recipient_urn (best-known). Gated: requires confirm:true. Returns a structured status. Counts against the daily message cap.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Must be true to actually execute. Omit/false = refuse (safety). |
| message | string | yes | Message body (multiline supported) |
| recipient_urn | string | – | Recipient member URN (urn:li:fsd_profile:ACoAA…). Required when starting a NEW thread. |
| thread_id | string | – | Existing thread id (2-…) or full msg_conversation urn to reply into (preferred over recipient_urn). |
No output schema declared.
No examples provided.
whoami ~19
Report server version, browser/login status, and capabilities.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
What is the io.github.devag7/linkedin-mcp server?
io.github.devag7/linkedin-mcp is listed in the public MCP registry as io.github.devag7/linkedin-mcp. LinkedIn for AI assistants, search, profiles, jobs, feed, messaging, and gated writes. This page covers its npm package (linkedin-mcp-tools).
Is the io.github.devag7/linkedin-mcp server safe to use?
io.github.devag7/linkedin-mcp scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.devag7/linkedin-mcp server expose?
io.github.devag7/linkedin-mcp exposes 22 tools: whoami, health_check, close_session, get_my_profile, get_profile, and 17 more. Their descriptions and schemas cost roughly 1,406 tokens of context every time the server is loaded.
Is the io.github.devag7/linkedin-mcp server still maintained?
io.github.devag7/linkedin-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.devag7/linkedin-mcp server under?
io.github.devag7/linkedin-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.