OTP/OJP MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OTP/OJP MCP Server Parse this resume into an OTP skeleton"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OTP/OJP MCP Server
An MCP server for the Open Talent Protocol (OTP) and Open Job Protocol (OJP) — open standards for structuring candidate profiles and job postings for AI agent reasoning.
Tools
Tool | Description |
| Raw resume text → OTP skeleton with |
| Validate an OTP document against the JSON Schema |
| Extract an agent-friendly summary from an OTP document |
| Raw job posting text → OJP skeleton with |
| Validate an OJP document against the JSON Schema |
| Extract an agent-friendly summary from an OJP document |
Related MCP server: genpark-structured-extract-schema-validator-skill
Key traits
Pure functions — no LLM calls, no network calls, no API keys needed
JSON Schema draft 2020-12 validation via AJV
LLM-free parsers — produce structured templates for the calling agent to complete
Zero config — just install and run
Install
npm install -g @opentalentprotocol/mcp-serverOr run directly with npx:
npx @opentalentprotocol/mcp-serverSetup
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"otp-ojp": {
"command": "npx",
"args": ["-y", "@opentalentprotocol/mcp-server"]
}
}
}Claude Code
Add to your project or global MCP settings:
{
"mcpServers": {
"otp-ojp": {
"command": "npx",
"args": ["-y", "@opentalentprotocol/mcp-server"]
}
}
}From source
git clone https://github.com/neogene-ai/otp-ojp-mcp-server.git
cd otp-ojp-mcp-server
npm install
npm run build
node dist/index.jsHow it works
Parsing workflow
The parsers follow a skeleton + fill pattern:
Call
otp_parse_resume(orojp_parse_job_posting) with raw textGet back a document skeleton with
_EXTRACT_*annotations, confidence levels, and known gapsThe calling agent fills in the skeleton using its own reasoning
Call
otp_validate_profile(orojp_validate_job_posting) to verify the result
This keeps the MCP server LLM-free while giving agents structured guidance on what to extract.
Introspection
The introspect tools flatten an OTP/OJP document into a normalized, agent-friendly object with an agentSummary string — ready for system prompts, retrieval-augmented context, or matching logic.
Schemas
The JSON Schemas are bundled in the schema/ directory:
schema/opentalent-protocol.schema.json— OTP v0.1schema/openjob-protocol.schema.json— OJP v0.1
Requirements
Node.js >= 18
License
MIT
Available Tools
5 toolsojp_introspect_job_postingA
Extract a structured, agent-friendly summary of an Open Job Protocol document. Returns normalized requirements, compensation, location, team, process details, and an agentSummary string suitable for use in a system prompt. Provide either filePath or document.
Inputs: document, filePath.
ojp_parse_job_postingA
Produce a structured OJP extraction template from raw job posting text. Returns a document skeleton with EXTRACT* annotations, a fieldConfidence list (high/medium/low per field), and a gaps list of information commonly missing from postings. The calling agent should fill in the skeleton using its reasoning over the text, then call ojp_validate_job_posting to verify the result.
Inputs: text (required), sourceUrl.
ojp_validate_job_postingA
Validate a JSON document against the Open Job Protocol schema (v0.1). Provide either filePath (absolute path to a .json file) or document (pre-parsed object). Returns validity status and a list of errors.
Inputs: document, filePath.
otp_parse_resumeA
Produce a structured OTP extraction template from raw resume text. Returns a document skeleton with EXTRACT* annotations, a fieldConfidence list (high/medium/low per field), and a gaps list of information not typically on resumes. The calling agent should fill in the skeleton using its reasoning over the text, then call otp_validate_profile to verify the result.
Inputs: text (required).
otp_validate_profileA
Validate a JSON document against the Open Talent Protocol schema (v0.1). Provide either filePath (absolute path to a .json file) or document (pre-parsed object). Returns validity status and a list of errors.
Inputs: document, filePath.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a distinct purpose clearly indicated by the name: OTP vs OJP, then validate, parse, or introspect. No two tools overlap in function.
All tools follow a consistent pattern of 'protocol_action_target' in snake_case, e.g., otp_validate_profile, ojp_parse_job_posting. No deviations.
5 tools cover two protocols (OTP and OJP) with essential operations: validation, parsing, and introspection (for OJP). The count feels well-scoped for the domain.
The set covers validation and parsing for both protocols, plus introspection for OJP. A minor gap is the lack of an introspection tool for OTP, but the stated purpose is sufficiently served.
Maintenance
Related MCP Connectors
Turn messy text into strict JSON schemas agents can trust (invoice, receipt, contact, resume).
Deterministic JSON repair, validate, example-gen, schema-coerce for agents. Zero LLM, sub-10ms.
Agent-native document parsing: PDF, scans and FR/EU invoices to structured JSON or Markdown.
300+ deterministic data utilities for AI agents: validate, normalize, parse, match, redact.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to access document processing tools for extracting text, generating summaries, and identifying skills via MCP.-
- FlicenseNot gradedqualityBmaintenanceEnables agents to deterministically extract structured entities from input payloads and validate or coerce them against JSON schemas, returning a standardized response dossier with execution telemetry. It runs as a zero-dependency MCP server that plugs into Claude Desktop, Cursor, and other MCP clients.8-

Civify MCP Serverofficial
AlicenseAqualityBmaintenanceEnables AI agents to parse resumes, tailor CVs, score ATS compatibility, redact PII, scrape job postings, and track applications through a career platform.8AGPL 3.0- FlicenseNot gradedqualityNot gradedmaintenanceEnables agents and MCP clients to deterministically extract and repair JSON/schema issues such as truncated braces, markdown wrappers, and invalid types without LLM round-trips.-