AI Research Assistant MCP Server
An MCP-based AI agent that retrieves and processes documents to answer queries using a RAG pipeline with LangChain and Claude models. It enables document indexing, context-aware retrieval, and multi-tool orchestration for research and knowledgebase applications.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
sagarkpoojary
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
search_jobsFetch jobs using JSearch API and store them temporarily. Return key info.
save_jobSave a specific job from temporary list into candidate's saved folder. If salary is not provided, it tries to extract it from the fetched job data.
ingest_pdfIngest PDF from folder, file path, or URL Args: source: Can be: - Folder path: processes all PDFs in folder - File path: processes single PDF - URL: downloads and processes PDF Returns: Status and number of chunks added
retrieveRetrieve top N chunks for given query Args: query: Search query n: Number of chunks to retrieve Returns: Top N matching chunks with scores
db_infoGet ChromaDB and collection information Returns: Database and collection statistics
clear_dbClear all data from database Returns: Confirmation message
save_research_dataSave research content to vector database for future retrieval. Args: content: List of text content to save topic: Topic name for organizing the data (creates separate DB)
search_research_dataSearch through saved research data using semantic similarity. Args: query: Search query topic: Topic database to search in max_results: Maximum number of results to return
list_research_topicsList all available research topics (vector databases).
delete_research_topicDelete a research topic and all its data. Args: topic: Topic name to delete
get_topic_infoGet detailed information about a research topic. Args: topic: Topic name to get info for
addAdd two numbers
get_weatherGet current weather for a location
get_forecastGet 3-day weather forecast
multiplyMultiply two numbers
subtractSubtract two numbers
divideDivide two numbers
RAPIDAPI_KEYRAPIDAPI_HOSTOPENAI_API_KEYexport =...CLAUDE_API_KEYexport =...FIRECRAWL_API_KEYTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
31/31 tools missing one or more hints — search_jobs (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); save_job (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ingest_pdf (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +28 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Destructive tools are labelled
2 tools perform destructive updates without destructiveHint — delete_research_topic deletes at line 224 (shutil.rmtree(topic_path)); delete_research_topic deletes at line 224 (shutil.rmtree(topic_path))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
2 tools describe read intent but their handlers mutate — search_jobs (line 78: with open(temp_path, "w") as f:); save_job (line 179: with open(job_file, "w") as f:)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
27/31 tool handlers declare input schemas (87%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 14/31 tool handlers wrap calls in try/catch (45%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Tool description accuracy
search_jobs: description implies read-only but handler writes/deletes/executes; save_job: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/sagarkpoojary/sagar-mcp-project)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check