Parallect MCP Server
Enables AI assistants to perform multi-provider deep research via Parallect.ai, including submitting queries, tracking progress, and retrieving synthesized reports with citations and evidence chains.
Caution. Specific findings reduced this grade. They are listed on the page. 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
securecoders
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.
balanceCheck current credit balance and optionally view recent transactions.
follow_upPursue a follow-on research question from a completed job's suggestions, or ask a custom follow-up in the same thread.
get_claim_evidenceGet the full evidence chain for a specific claim, including all supporting sources, their URLs, snippets, and the claim's history of events.
get_resultsGet the synthesized results of a completed research job. Returns the unified report with [src_N] inline citations, a sourceRegistry to resolve those citations to URLs, follow-on suggestions, and cost breakdown. Set includeClaimsJson to get first-class claims with source links and confidence scores.
get_threadGet a specific research thread with all messages, jobs, and results.
list_providersList available research providers, their models, capabilities, and the default provider assignments per budget tier.
list_threadsList recent research threads for the authenticated user.
research_statusCheck the status of a research job. Returns progress for each provider and overall job status.
researchSubmit a deep research query. Always creates a new research thread. To follow up on existing research, use the follow_up tool instead. Fans out to multiple AI research providers and synthesizes results into a unified report with cross-referenced citations and conflict resolution.
search_claimsSearch for claims across research jobs. Can search by text content, filter by confidence level, or list all claims for a thread.
usageGet usage analytics: spend by provider, job count, average cost per query.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
MCP_PUBLIC_URLPARALLECT_API_KEY"": "par_live_your_key_here"PARALLECT_API_URLPORT=8080 =https://parallect.ai npm run start:httpPORTTool 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
11/11 tools missing one or more hints — balance (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); follow_up (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_claim_evidence (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 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.
Tool handlers catch errors
7/11 tool handlers wrap calls in try/catch (64%)
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.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Domain consistency
npm scope @parallect doesn't match GitHub owner securecoders
Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.
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/securecoders/parallect-mcp)?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