← Back to search

io.github.CSOAI-ORG/linkedin-outreach-mcp

CSOAI-ORG Scanned 18h ago

AI-powered linkedin outreach MCP server for agents. Supports generate connection request, ge...

C
71.4 / 100

Versions

No versions found.

PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 6

generate_connection_request
annotations: none low

Generate a personalized LinkedIn connection request (max 300 characters). Returns 3 variants to choose from. Edit and personalize before sending. Args: name: Target person's full name title: Their job title (e.g. "VP of Engineering") company: Their company name shared_interests: Comma-separated shared interests or topics context: Optional extra context (e.g. "met at SaaStr conference") Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

name str title str api_key str company str context str shared_interests str
generate_inmessage
annotations: none low

Generate a professional LinkedIn InMail or direct message. Args: recipient_name: Recipient's full name recipient_title: Their job title conversation_context: Any prior context (e.g. "they liked my post about AI") goal: What you want to achieve (e.g. "book a demo call", "discuss job opportunity") tone: Message tone -- one of: casual, professional, sales, recruiting Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

goal str tone str api_key str recipient_name str recipient_title str conversation_context str
generate_post
annotations: none low

Generate an engaging LinkedIn post with hashtags. Args: topic: The main topic or theme of the post key_points: Comma-separated key points to include style: Post style -- one of: thought-leadership, announcement, question, story Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

style str topic str api_key str key_points str
analyze_profile
annotations: none low

Analyze a LinkedIn profile description to extract actionable outreach insights. Extracts: industry, seniority level, likely pain points, conversation starters, and mutual interest areas. Use this before crafting your outreach. Args: profile_text: The person's LinkedIn headline, summary, or About section text Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

api_key str profile_text str
generate_outreach_sequence
annotations: none low

Generate a 5-touch LinkedIn outreach sequence with timing recommendations. Sequence: connection request -> value message -> case study -> soft ask -> direct ask. Each touch includes the message text, timing, and strategic goal. Args: target_name: Target person's full name target_title: Their job title target_company: Their company target_industry: Their industry (auto-detected from title if blank) goal: Your outreach goal (e.g. "book a demo", "recruit for senior role") Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

goal str api_key str target_name str target_title str target_company str target_industry str
generate_comment
annotations: none low

Generate an insightful comment for a LinkedIn post. Analyzes the post type (question, achievement, opinion, advice, story) and generates comments that add genuine value -- not generic "Great post!" fluff. Args: post_content: The text content of the LinkedIn post you want to comment on Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for real-time production decision-making without human review of results.

api_key str post_content str

Permissions 3

network medium
Server uses network capabilities via: urllib
filesystem low
Server uses filesystem capabilities via: os
env_vars low
Server uses env_vars capabilities via: os.environ

Scan Findings 34

info
Required env vars (5) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
low
Tool 'generate_post' has no annotations annotation_checker · 100%
low
Tool 'generate_connection_request' has no annotations annotation_checker · 100%
low
Tool 'generate_inmessage' has no annotations annotation_checker · 100%
low
Tool 'analyze_profile' has no annotations annotation_checker · 100%
low
Tool 'generate_outreach_sequence' has no annotations annotation_checker · 100%
low
Tool 'generate_comment' has no annotations annotation_checker · 100%
high
Remote transport without authentication auth_checker · 70%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-3qhf-m339-9g5v) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-9h52-p55h-vw2f) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-j975-95f5-7wqh) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-jpw9-pfvf-9f58) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (GHSA-vj7q-gjh5-988w) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-1616) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-1617) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-1618) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-3482) dependency_analyzer · 95%
medium
Vulnerable dependency: mcp@1.0.0 (PYSEC-2026-3483) dependency_analyzer · 95%
info
package.json metadata manifest_parser · 100%
info
pyproject.toml metadata manifest_parser · 100%
info
Tool: generate_connection_request manifest_parser · 90%
info
Tool: generate_inmessage manifest_parser · 90%
info
Tool: generate_post manifest_parser · 90%
info
Tool: analyze_profile manifest_parser · 90%
info
Tool: generate_outreach_sequence manifest_parser · 90%
info
Tool: generate_comment manifest_parser · 90%
info
Transport: streamable-http manifest_parser · 80%
medium
Permission: network access detected permission_analyzer · 80%
low
Permission: filesystem access detected permission_analyzer · 70%
low
Permission: env_vars access detected permission_analyzer · 90%
info
No dependency files found for SBOM generation sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%