Linkedin (stickerdaniel) MCP Server
mcp-server-linkedin
PyPI
v4.23.3
Published by stickerdaniel — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
MCP server that gives AI assistants like Claude access to LinkedIn profiles, companies, and job postings through the user's own browser session.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 12
high Reads a sensitive credential path or dumps the environment (linkedin_mcp_server/daemon_owner.py)MTC-SRC-006
In the server's implementation (`linkedin_mcp_server/daemon_owner.py:299`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: env=False`` also drops ``.netrc`` and environment certificate settings, none of which have any business on a loopbac
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/daemon_owner.py
high Shell/command execution in server code (linkedin_mcp_server/browser_downgrade.py)MTC-SRC-002
In the server's implementation (`linkedin_mcp_server/browser_downgrade.py:346`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: finished = subprocess.run( [executable, "--version"], capture_output=True,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/browser_downgrade.py
high Shell/command execution in server code (linkedin_mcp_server/browser_import/extract.py)MTC-SRC-002
In the server's implementation (`linkedin_mcp_server/browser_import/extract.py:129`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: y: result = subprocess.run( argv, capture_output=True, check=False, timeout=10.0
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/browser_import/extract.py
high Shell/command execution in server code (linkedin_mcp_server/daemon_election.py)MTC-SRC-002
In the server's implementation (`linkedin_mcp_server/daemon_election.py:854`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ) child = subprocess.Popen( command, env=_owner_environment(), stdin=s
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/daemon_election.py
high Shell/command execution in server code (linkedin_mcp_server/installer_supervisor.py)MTC-SRC-002
In the server's implementation (`linkedin_mcp_server/installer_supervisor.py:178`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: TH", None) worker = subprocess.Popen( worker_command, stdin=subprocess.PIPE, stdout=None,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/installer_supervisor.py
high Shell/command execution in server code (linkedin_mcp_server/installer_worker.py)MTC-SRC-002
In the server's implementation (`linkedin_mcp_server/installer_worker.py:78`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: target = subprocess.Popen( _command(argv), # Never the lease. The thread above ho
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/installer_worker.py
high Shell/command execution in server code (linkedin_mcp_server/login_viewer.py)MTC-SRC-002
In the server's implementation (`linkedin_mcp_server/login_viewer.py:196`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ") result = subprocess.run( ["obxprop", "--root", "_NET_SUPPORTING_WM_CHECK"],
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/login_viewer.py
high Shell/command execution in server code (linkedin_mcp_server/process_gate.py)MTC-SRC-002
In the server's implementation (`linkedin_mcp_server/process_gate.py:48`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: target = subprocess.Popen( command, stdin=0, stdout=1, st
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/process_gate.py
high Shell/command execution in server code (linkedin_mcp_server/process_guardian.py)MTC-SRC-002
In the server's implementation (`linkedin_mcp_server/process_guardian.py:58`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: snapshot = subprocess.run( [ps, "eww", "-A", "-o", "pid=", "-o", "pgid=", "-o", "command="],
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/process_guardian.py
high Shell/command execution in server code (linkedin_mcp_server/process_tree.py)MTC-SRC-002
In the server's implementation (`linkedin_mcp_server/process_tree.py:108`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: process = subprocess.Popen( [ sys.executable, "-I",
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server linkedin_mcp_server/process_tree.py
low Shell/command execution in packaging/dev tooling (tests/test_bootstrap.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_bootstrap.py:2484`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: [()] async def spawn(*_args: object, **_kwargs: object) -> _FakeProc: # Everything lands at once, i
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_bootstrap.py
low Dynamic module load from a non-literal in packaging/dev tooling (tests/test_greenlet_runtime.py)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_greenlet_runtime.py:339`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: l" if {on_windows} else __import__( "ctypes.util", fromlist=["find_library"] ).find_library("c") ctypes.CDLL = _cdll
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_greenlet_runtime.py
Tools 19
Each tool and what it can reach — statically extracted from the published source.
send_messagenetwork egressclose_sessionno sensitive capabilityconnect_with_personno sensitive capabilityget_company_employeesno sensitive capabilityget_company_postsno sensitive capabilityget_company_profileno sensitive capabilityget_conversationno sensitive capabilityget_feedno sensitive capabilityget_inboxno sensitive capabilityget_job_detailsno sensitive capability
Show 9 more tools ↓
get_my_profileno sensitive capabilityget_person_profileno sensitive capabilityget_saved_jobsno sensitive capabilityget_sidebar_profilesno sensitive capabilitysearch_companiesno sensitive capabilitysearch_conversationsno sensitive capabilitysearch_jobsno sensitive capabilitysearch_peopleno sensitive capabilitysearch_postsno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (19 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 9
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v4.23.3 latest |
A 93/100 | 12 | 1.13.0 | 2026-09-04 |
v4.23.1 |
A 93/100 | 12 | 1.13.0 | 2026-08-25 |
v4.23.0 |
A 93/100 | 12 | 1.12.1 | 2026-08-22 |
v4.22.0 |
A 93/100 | 12 | 1.12.1 | 2026-08-12 |
v4.21.0 |
A 93/100 | 12 | 1.12.1 | 2026-08-10 |
Show 4 more versions ↓
v4.20.1 |
A 93/100 | 8 | 1.12.1 | 2026-07-31 |
v4.20.0 |
A 93/100 | 7 | 1.12.1 | 2026-07-29 |
v4.19.0 |
A 93/100 | 2 | 1.12.1 | 2026-07-27 |
v4.17.0 |
A 93/100 | 2 | 1.9.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan mcp-server-linkedin --online --registry pypiOther implementations of Linkedin 20
Independent packages implementing the same tool, scanned with the same engine. Compare all 21 side by side →
LinkedIn Ads MCP Server - Campaign entity management and reporting via LinkedIn Marketing API v2
LinkedIn MCP server — publish posts, articles, and media via the LinkedIn API
MCP server for LinkedIn API via HarvestAPI - Returns cleaned data in TOON format for token efficiency
MCP server for LinkedIn — post, comment, react, and manage content via AI agents
MCP server for linkedin API integration
MCP server for posting to LinkedIn via the LinkedIn API using an OAuth access token
More in Marketing & Social
Official Abyssfall game info, newsletter double opt-in, and merch reservation tools.
AdCritter ads platform: docs, API reference, app scaffolding, and white-label integration.
Google AdSense MCP Server - Monitor earnings, reports, and account health via Claude/AI
Operational empathy for technical founders + PE/VC operators navigating high-stakes B2B interactions. 28 MCP tools + CLI: ICP scoring, persona simulation, battlecards, deal classification, prospect discovery, investor matching, founder wellness, plus mark
MCP server for Bing Webmaster Tools — SEO site management, URL submission, sitemaps, stats, keywords
MCP (Model Context Protocol) server that helps AI agents use Primer Brand (@primer/react-brand) correctly when building GitHub marketing and landing pages.