Kiro Conversations MCP (Wil-Collier/kiro-conversations-mcp) is an MCP server listed on the M8ven Trust Index. It scores 58 out of 100, grade D. It declares 9 tools. No publisher has claimed this listing.
A local MCP server for durable, named Kiro CLI conversations over ACP, enabling asynchronous runs with session management, model querying, and bounded wait delegation.
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
Wil-Collier
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.
kiro_delegateCommon convenience path: start or resume a named Kiro conversation, then wait until its run reaches a terminal state. If this MCP request is interrupted, the durable run continues and may be reattached with kiro_wait.
kiro_startStart an asynchronous turn in a named Kiro conversation. Returns an opaque runId plus a safe summary of the persisted session and its immutable settings.
kiro_modelsList the canonical model IDs currently available from the local Kiro CLI. Use these IDs for new Kiro conversations; uniquely resolvable shorthand aliases are normalized to their canonical ID.
kiro_waitWait until a run reaches a terminal state. If this MCP request is interrupted, the durable run continues and may be reattached later. runId may be omitted only when the session has one active run or a latest unconsumed completed run; ambiguous or stale lookups fail safely.
kiro_resultReturn a normalized safe run result without waiting. runId may be omitted only under deterministic active/latest-unconsumed resolution; explicit runId remains supported.
kiro_statusReturn a compact safe dashboard of persisted session settings, active and recent run status/phase, computed elapsed time, and redacted terminal outcomes. It reports no inferred ACP semantics.
kiro_cancelCancel a specific active run and wait for cancellation to become durable.
kiro_sessionsList safe persisted conversation metadata with cursor pagination.
kiro_closeCancel any active run and close a named conversation without exposing or deleting Kiro's internal session.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
@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
KIRO_ACP_AUTH_METHODKIRO_ACP_MAX_REPLY_BYTESKIRO_ACP_MAX_RETAINED_RUNSKIRO_ACP_PERSIST_REPLIESKIRO_CLI_PATHKIRO_CONVERSATIONS_ACP_STATE_DIRKIRO_CONVERSATIONS_SANDBOX_TMPKIRO_CONVERSATIONS_TIMEOUT_MSTool 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
9/9 tools missing one or more hints — kiro_delegate (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); kiro_start (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); kiro_models (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +6 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 inputs are validated
Only 2/9 tool handlers declare input schemas (22%)
Declare an inputSchema with zod/joi/yup on every tool definition.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.21.0 (high), @modelcontextprotocol/sdk@1.21.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
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/wil-collier/kiro-conversations-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