iris-agent (4onstudios/iris-agent) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 1 tool. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100

iris-agent

Open-source TypeScript coding agent with CLI, HTTP API, ACP, LSP, MCP, workspace tools, and multi-provider model support.

→ 4onstudios/iris-agent· listed on github_repo_search

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

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

4onstudios

Source: github_repo_search

Is this your MCP?

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 →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

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.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 4 credentials: HF_TOKEN, IRIS_DESKTOP_TOKEN, OLLAMA_API_KEY, OPENROUTER_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configAGENT_ALLOWED_ORIGINSwith the IDE's origin when browser CORS is required:
configANTHROPIC_BETAOptional Anthropic beta headers.
configANTHROPIC_BETASOptional Anthropic beta headers.
🔐 secretHF_TOKENHugging Face authentication where required by a configured provider.
configIRIS_AGENT_AUTO_FIX_VALIDATIONEnable automatic validation fixes.
configIRIS_AGENT_AUTO_LINTEnable automatic lint/test validation.
configIRIS_AGENT_AUTO_TESTEnable automatic lint/test validation.
configIRIS_AGENT_EXTERNAL_AGENT_MANIFEST_PATHPath to an external-agent manifest.
configIRIS_AGENT_GIT_SAFETY_MODEGit safety policy; defaults to suggest.
configIRIS_AGENT_GOAL_JUDGE_MODEL
configIRIS_AGENT_INPUT_TOKEN_LIMITToken-budget controls.
configIRIS_AGENT_LINT_CMDOverride validation commands.
configIRIS_AGENT_MAX_OUTPUT_TOKENSToken-budget controls.
configIRIS_AGENT_MODEL_RETRY_ATTEMPTSModel request retry count.
configIRIS_AGENT_PREFERRED_AGENT_IDPreferred external agent identifier.
configIRIS_AGENT_PROMPT_TOKEN_BUDGET_RATIOPrompt budget ratio.
configIRIS_AGENT_REFLECTION_MAXReflection-loop limits.
configIRIS_AGENT_REFLECTION_MAX_STEPSReflection-loop limits.
configIRIS_AGENT_REFLECTION_NO_PROGRESS_REPEATSMaximum repeated no-progress reflection cycles.
configIRIS_AGENT_REFLECTION_RETRY_ATTEMPTSReflection retry count.
configIRIS_AGENT_RUNS_DB_PATHSQLite path for persisted run lifecycle data.
configIRIS_AGENT_STREAM_RETRY_BASE_DELAY_MS
configIRIS_AGENT_STREAM_RETRY_ENABLEDEnable stream retries. Related retry delay and limit variables are supported by the runtime.
configIRIS_AGENT_STREAM_RETRY_MAX_DELAY_MS
configIRIS_AGENT_STREAM_RETRY_MAX_RETRIES
configIRIS_AGENT_STREAM_RETRY_UNKNOWN_ERRORS
configIRIS_AGENT_TEST_CMDOverride validation commands.
configIRIS_BACKEND_SERVICESelects the backend service integration.
configIRIS_DEBUG_TOKEN_USAGE_SOURCEEnable token-usage diagnostics.
🔐 secretIRIS_DESKTOP_TOKENDesktop-only routes require both TAURI_BUNDLED=1 and .
configIRIS_ENABLE_SLASH_COMMANDSEnable slash-command handling.
configIRIS_LSP_APPROVED_SHA256_JSON
configIRIS_LSP_SYSTEM_SERVER_OVERRIDE_JSON
configIRIS_VERBOSE_SKILL_DISCOVERYEnable verbose skill-discovery logging.
configMODEL_IDmodelId - Model identifier used for chat/ACP sessions (default: openrouter/openai/gpt-4o or / OPENROUTER_MODEL env vars)
🔐 secretOLLAMA_API_KEY
configOLLAMA_BASE_URLOllama-compatible server URL.
🔐 secretOPENROUTER_API_KEYSet OPENAI_API_KEY, , or the API key for the selected
configOPENROUTER_BASE_URLOpenRouter-compatible API URL.
configOPENROUTER_DEBUG_ECHO_UPSTREAM_BODY
configOPENROUTER_MODELmodelId - Model identifier used for chat/ACP sessions (default: openrouter/openai/gpt-4o or MODEL_ID / env vars)
configOPENROUTER_SITE_NAMEOptional OpenRouter request metadata.
configOPENROUTER_SITE_URLOptional OpenRouter request metadata.
configTAURI_BUNDLEDDesktop-only routes require both =1 and IRIS_DESKTOP_TOKEN.
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployDATABASE_URL
deployPORT
// quality suggestions

Dependencies

21 runtime dependencies (14 dev), 1 flagged: puppeteer

Tool 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

1/1 tools missing one or more hints — read_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). 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.

Shell command execution

1 call in production code run through a shell (bin/iris-agent.js:17)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Secrets not logged

5 secret values sent to log

Redact or omit secret values from log output.

Dependency freshness

1/21 production deps stale: json-schema@2022-06-19 (4.2y)

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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/4onstudios/iris-agent)](https://m8ven.ai/mcp/4onstudios/iris-agent)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: cff9bb7c4ca5fc8ab62134665a47e31b1e884dc4
code hash: 76150884eb9408448b9233c90aa0070fc2b70c7399ced9bbcf7e5fa3ff518a56
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client