Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.Ruthvik-Bandari/linkedin-profile-mcp

NPM · LINKEDIN-PROFILE-MCP

Review and improve LinkedIn profile text the way recruiters search. No scraping or login.

+6 this week 73 Trust /100

Last scanned (21 hours ago)

Scores higher than 46% of npm servers

Category Marketing and SEO

Trust breakdown (7 categories)

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 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability61
  • 50% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1348 tokens (~168/item across 8 items; 6 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management43
  • Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 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
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 19 Nov 26 +6
    • Stability: unverified → 0.37 ▲ functional
  • 9 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 8 Nov 26 52

    First indexed and scored.

Diagnostics

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 21 Nov 2026 · Analysed npm/linkedin-profile-mcp@0.1.1

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 92 packages
Packages resolved 92
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~1,340 tokens

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 →

Tool Tokens
get_guidelines ~129

Return LinkedIn profile writing guidelines based on how technical recruiters search. Use this before drafting or rewriting a section; it is reference text and does not check anything (use lint_field or the review_* tools to check text). Returns plain text: rules, character limits and examples for one section, or the whole guide when 'section' is omitted. Read-only, no network.

NameTypeReqDescription
sectionstring–Which section to return, e.g. 'headline', 'about', 'experience', 'open_to_work', 'skills', 'checklist'. Omit to get every section in one text.

No output schema declared.

No examples provided.

keyword_coverage ~210

Compare a profile with target job postings. Use it first when the user has job descriptions: it finds single words and two-word phrases that recur across the postings (in at least 2 postings when 3 or more are given) and reports which ones appear in the profile. Feed the results to review_headline and review_experience as 'keywords'. Returns JSON: { covered: [{ term, inPostings, inProfile }], missing: [...], coverage: '<n> of <m> ...' }, ranked by how many postings use each term. Only suggest adding a missing term if it truly describes the person's work. Read-only, no network.

NameTypeReqDescription
job_descriptionsarrayyesFull text of 1 to 10 target job postings, one string per posting
profile_textstringyesHeadline, About, Experience and Skills pasted together as plain text
topinteger–How many recurring terms to report, 5 to 80. Default 30.

No output schema declared.

No examples provided.

lint_field ~238

Check the text of one LinkedIn field (or a post, comment or connection note) before the user pastes it. Use for any single field; for a headline or an Experience entry prefer review_headline or review_experience, which run these checks plus structure checks. Checks the character limit, em and en dashes, stock phrases that read as AI-written, the 'it's not X, it's Y' pattern, '-' list markers and emoji, and shows the text visible before 'see more'. Returns JSON: { field, characters, limit, issues: [{ severity: 'error' | 'warn' | 'tip', message }] }; errors must be fixed, warnings should be. Read-only, no network.

NameTypeReqDescription
fieldstringyesWhich field the text is for; this sets the limit. headline 220, about 2600, experience_title 100, experience_description 2000, featured_title ~45, featured_description ~200, post 3000, comment 1250,…
textstringyesThe exact text of the field, as it would be pasted into LinkedIn

No output schema declared.

No examples provided.

review_experience ~216

Review the description of one LinkedIn Experience entry (one role). Use it once per role; use review_profile to check every role together with the rest of the profile. Pass/fail checks: at least 300 characters, an opening line that explains the role on its own, 3 to 7 bullets, most bullets with a number, most bullets starting with an action verb, and target keywords; it also warns on duty phrasing ('responsible for', 'worked on') and runs all lint_field checks. Returns JSON: { characters, limit, issues: [...], bullets, bulletsWithNumbers, bulletsStartingWithVerb, checks: [{ name, pass, detail }] }. Read-only, no network.

NameTypeReqDescription
descriptionstringyesThe full description text of one role, up to 2,000 characters. Bullets may start with '•', '-' or '*'.
keywordsarray–Target terms from job postings. Passes when at least a third of them appear. Get them from keyword_coverage.

No output schema declared.

No examples provided.

review_headline ~234

Review a LinkedIn headline against recruiter-search rules. Use this for headlines instead of lint_field; use review_profile to check a whole profile at once. Runs pass/fail checks: not a vague label ('Student at X', 'Aspiring'), target role in the first 60 characters, at least 150 of 220 characters used, 3 or more segments separated by '|', an 'Open to ... roles' line, and target keywords present; plus all lint_field checks. Returns JSON: { characters, limit, issues: [...], checks: [{ name, pass, detail }] }. Rewrite and call again until every check passes. Read-only, no network.

NameTypeReqDescription
headlinestringyesThe full headline text, up to 220 characters
keywordsarray–Must-have terms from target job postings, e.g. ['Python', 'RAG']. Passes when at least 2 appear. Get them from keyword_coverage.
target_rolestring–The job title the person wants, e.g. 'AI Engineer'. Enables the 'role in the first 60 characters' check.

No output schema declared.

No examples provided.

review_profile ~313

Review a whole LinkedIn profile in one call. Use it for a first full review; then use review_headline, review_experience or lint_field on single sections while rewriting. Split the user's pasted profile (for example the text of LinkedIn's 'Save to PDF') into the fields below. Runs review_headline, lint_field on About, review_experience on each role, keyword_coverage when job descriptions are given (its top 12 terms become the keywords for the other checks), and a checklist. Returns JSON: { headline, about, experiences: [{ title, company, titleLint, review }], keywordCoverage, checklist: [{ item, pass }] }. Read-only; never logs in to or scrapes LinkedIn.

NameTypeReqDescription
aboutstring–The About section text
connectionsinteger–Number of connections (use 500 for '500+')
experiencesarray–Each Experience entry, most recent first
featured_countinteger–How many items are in the Featured section
headlinestringyesThe headline text
job_descriptionsarray–Full text of 1 to 10 target job postings, one string per posting
locationstring–The location shown on the profile, e.g. 'Boston, MA'. A country alone fails the checklist.
skillsarray–Every listed skill, one per item
target_rolestring–The job title the person wants, e.g. 'Data Scientist'

No output schema declared.

No examples provided.

Install

How do I install the io.github.Ruthvik-Bandari/linkedin-profile-mcp server?

io.github.Ruthvik-Bandari/linkedin-profile-mcp runs locally as an npm package, launched with npx -y linkedin-profile-mcp. 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-profile-mcp

# add to Claude Code
claude mcp add ruthvik-bandari-linkedin-profile-mcp -- npx -y linkedin-profile-mcp
Common questions

What is the io.github.Ruthvik-Bandari/linkedin-profile-mcp server?

io.github.Ruthvik-Bandari/linkedin-profile-mcp is listed in the public MCP registry as io.github.Ruthvik-Bandari/linkedin-profile-mcp. Review and improve LinkedIn profile text the way recruiters search. No scraping or login. This page covers its npm package (linkedin-profile-mcp).

Is the io.github.Ruthvik-Bandari/linkedin-profile-mcp server safe to use?

io.github.Ruthvik-Bandari/linkedin-profile-mcp scores 73 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 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.Ruthvik-Bandari/linkedin-profile-mcp server expose?

io.github.Ruthvik-Bandari/linkedin-profile-mcp exposes 6 tools: get_guidelines, lint_field, review_headline, review_experience, keyword_coverage, review_profile. Their descriptions and schemas cost roughly 1,340 tokens of context every time the server is loaded.

Is the io.github.Ruthvik-Bandari/linkedin-profile-mcp server still maintained?

io.github.Ruthvik-Bandari/linkedin-profile-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 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.Ruthvik-Bandari/linkedin-profile-mcp server under?

io.github.Ruthvik-Bandari/linkedin-profile-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.

What did VerifyMCP test on the io.github.Ruthvik-Bandari/linkedin-profile-mcp server?

VerifyMCP ran 16 checks on io.github.Ruthvik-Bandari/linkedin-profile-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.