Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.runsec-io/mcp

NPM · @RUNSEC/MCP · SCANNED SEP 25

RunSec MCP server for workspace security scanning and remediation workflows.

Available components

0 this week 75 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security96
  • No malware found by supply-chain analysis.Pass
  • Known CVEs were checked across the 110 of 117 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Dependency health was assessed across the 110 of 117 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability74
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2352 tokens (~123/item across 19 items; 19 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_ephemeral_script" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.runsec-io/mcp server?

io.github.runsec-io/mcp runs locally as an npm package, launched with npx -y @runsec/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @runsec/mcp

# add to Claude Code
claude mcp add runsec-io-mcp -- npx -y @runsec/mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "runsec-io-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@runsec/mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "runsec-io-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@runsec/mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add runsec-io-mcp -- npx -y @runsec/mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "runsec-io-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@runsec/mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add runsec-io-mcp --command npx --arg -y --arg @runsec/mcp
# ~/.hermes/config.yaml
mcp_servers:
  runsec-io-mcp:
    command: "npx"
    args: ["-y", "@runsec/mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "runsec-io-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@runsec/mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add runsec-io-mcp -t stdio -c npx -a -y @runsec/mcp
// mcp.json
{
  "mcpServers": {
    "runsec-io-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@runsec/mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 25 Sept 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 22 Sept 26 0
    • Stability: 0.97 → pass security
  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 25 Sept 2026 · Analysed npm/@runsec/mcp@1.0.127

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 110 packages
Packages resolved 110
Stale 31
No linked repository 11
Tree resolution Partial

The dependency tree was only partially resolved, so these counts may be incomplete.

Background: SBOMs and build attestations, explained →

MCP tools · 19 exposed · ~2,352 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
execute_ephemeral_script ~224

Run a polyglot ephemeral security test: writes content to <workspace>/.runsec-temp/, executes command from workspace root (10s timeout), returns stdout/stderr, then deletes the script. Use {file} in command for script path.

NameTypeReqDescription
commandstringyesShell command to run from workspace root. Use {file} or {filepath} for the script path.
contentstringyesFull source code of the ephemeral test (mock DB / in-memory only).
filenamestringyesBasename for the ephemeral test file (e.g. test_bola_poc.py, poc_test.go).
finding_idstringyesThe ID of the finding you are trying to verify (e.g. django-cors-wildcard). This MUST match the id you will use in submit_agent_findings.
timeout_msnumber–Optional timeout in milliseconds (default 10000).
workspace_pathstringyesRepository root; script is written to .runsec-temp/ under this path and command runs with cwd here.

No output schema declared.

No examples provided.

execute_live_poc ~229

Execute a live HTTP request for API/network PoC validation (10s default timeout). Returns status, headers, and body (truncated at 256KB). Include finding_id matching submit_agent_findings — any completed HTTP response (including 4xx/5xx) records the PoC as executed for VERIFIED.

NameTypeReqDescription
bodystring–Optional request body (raw string; use with POST/PUT/PATCH).
finding_idstringyesThe ID of the finding you are verifying (e.g. api-bola-idor). Must match the id used in submit_agent_findings.
headersobject–Optional request headers as string key/value pairs.
methodstringyesHTTP method: GET, POST, PUT, PATCH, DELETE, HEAD, or OPTIONS.
timeout_msnumber–Optional timeout in milliseconds (default 10000, max 60000).
urlstringyesFull http:// or https:// URL to request (including path and query).
workspace_pathstringyesRepository root (for consistency with other verification tools).

No output schema declared.

No examples provided.

report_cognitive_feedback ~149

Train the adaptive cognitive filter: record a False Positive (FP → AI_VETOED) or True Positive (TP → CONFIRMED_TP) for a static hint fingerprint_hash from runsec-semantic-brief.json. After two FP vetoes the finding is auto-suppressed on future scans.

NameTypeReqDescription
fingerprint_hashstringyesSHA-256 fingerprint from static_hints[].fingerprint_hash in the semantic brief.
reasonstring–Optional rationale stored with the feedback entry.
verdictstringyesFP = agent vetoed false positive; TP = confirmed true positive.
workspace_pathstringyesRepository root where .runsec-adaptive-filter.json is stored.

No output schema declared.

No examples provided.

runsec_apply_remediation ~162

Apply a deterministic safe-pattern patch to a file. Verifies target_line_or_block matches exactly, validates replacement against Skills catalog, writes a .bak backup, then patches the file.

NameTypeReqDescription
file_pathstringyesRelative path to the file within the workspace.
replacement_codestringyesApproved secure replacement; must align with safe_pattern/fix_template from runsec_ask_guidance.
rule_idstringyesMetric or rule id from RunSec skills (e.g. DVS-001, PY-001, DOCK-010).
target_line_or_blockstringyesExact line or multi-line block currently in the file (must match before patch).
workspace_pathstringyesRepository root containing the target file.

No output schema declared.

No examples provided.

runsec_ask_guidance ~61

Semantic search over RunSec safe-pattern knowledge base. Returns top safe patterns and fix templates for a vulnerability description (anti-hallucination remediation).

NameTypeReqDescription
questionstringyesVulnerability description, metric id, or remediation question (natural language).

No output schema declared.

No examples provided.

runsec_audit_general ~122

Full workspace security audit (user intent: @runsec audit). Runs static engines plus mandatory agent architectural review (missing controls: auth, RBAC, rate limiting, CSRF, secrets-by-design). Writes runsec-semantic-brief.json; execute agent_instructions (7 phases incl. Step 2.5) and submit_agent_findings. Hub sync when API key is set.

NameTypeReqDescription
target_filesarray–Optional relative file paths to scan instead of full workspace.
workspace_pathstringyesAbsolute or relative path to repository root.

No output schema declared.

No examples provided.

runsec_audit_hipaa ~73

Run HIPAA safeguards audit (PHI/PII logging + integrity) against workspace files. Writes results to runsec-report.md.

NameTypeReqDescription
target_filesarray–Optional relative file paths to scan instead of full workspace.
workspace_pathstringyesAbsolute or relative path to repository root.

No output schema declared.

No examples provided.

runsec_audit_owasp ~62

Run OWASP audit against workspace files. Writes results to runsec-report.md.

NameTypeReqDescription
target_filesarray–Optional relative file paths to scan instead of full workspace.
workspace_pathstringyesAbsolute or relative path to repository root.

No output schema declared.

No examples provided.

runsec_audit_pcidss ~72

Run PCI-DSS v4.0 Req 6.5 audit against workspace files. Writes results to runsec-report.md.

NameTypeReqDescription
target_filesarray–Optional relative file paths to scan instead of full workspace.
workspace_pathstringyesAbsolute or relative path to repository root.

No output schema declared.

No examples provided.

runsec_audit_soc2 ~71

Run SOC2 logical-access audit (JWT/session + RBAC patterns) against workspace files. Writes results to runsec-report.md.

NameTypeReqDescription
target_filesarray–Optional relative file paths to scan instead of full workspace.
workspace_pathstringyesAbsolute or relative path to repository root.

No output schema declared.

No examples provided.

runsec_generate_review ~133

Penetration-tester / auditor report: runs a full GENERAL unified scan plus STRIDE threat modeling, then writes runsec-security-review.md (executive summary, business-risk findings, audit exclusions). English-only; distinct from runsec-report.md.

NameTypeReqDescription
contextstring–Optional deployment context (stack, integrations, regulatory scope) for STRIDE profiling.
project_namestring–Optional display name for the security review document header.
target_filesarray–Optional relative file paths to scan instead of the full workspace.
workspace_pathstringyesAbsolute or relative path to repository root.

No output schema declared.

No examples provided.

runsec_get_active_findings ~73

Retrieve active/open vulnerabilities from sealed .runsec-cache/report.json (user intent: @runsec fix active findings). Returns unsealed agent_findings and static_snapshot summary — use instead of reading report.json manually.

NameTypeReqDescription
workspace_pathstringyesRepository root where .runsec-cache/report.json is stored.

No output schema declared.

No examples provided.

runsec_get_context ~108

Return index.md and patterns.md for a skill_id, plus optional RAG hints and skill orchestration for a file or question.

NameTypeReqDescription
file_contentstring–Optional file snippet for orchestration scoring.
file_pathstring–Optional file path for skill orchestration scoring.
questionstring–Optional question to fetch RAG hints within the skill.
skill_idstringyesSkill identifier (e.g. fastapi-async, nodejs-nestjs).

No output schema declared.

No examples provided.

runsec_get_semantic_targets ~133

Return high-value authorization/business-logic review targets, expert prompts (DRF/FastAPI/Flutter baselines), and JSON finding schema for the IDE agent. No remote LLM calls — the Cursor agent performs semantic review locally.

NameTypeReqDescription
contextstring–Optional deployment/architecture notes to refine profile detection.
include_static_baselineboolean–When true (default), run a quick static merge pass to rank targets against Semgrep hits.
target_filesarray–Optional relative file paths to scope target selection.
workspace_pathstringyesAbsolute or relative path to repository root.

No output schema declared.

No examples provided.

runsec_ignore_finding ~175

Persist an accepted false positive to .runsecignore.yaml (rule_id + file_path + line SHA256). Matching findings are excluded from future Semgrep audits in this workspace.

NameTypeReqDescription
file_pathstringyesRelative path to the file within the workspace.
line_contentstring–Exact source line at the finding (used to compute SHA256 fingerprint).
line_sha256string–Precomputed SHA256 of line_content; use instead of line_content when already known.
reasonstring–Optional justification stored in .runsecignore.yaml.
rule_idstringyesSemgrep rule id or metric token (e.g. PY-001, runsec.domain-input-validation.cwe-89).
workspace_pathstringyesRepository root where .runsecignore.yaml will be written.

No output schema declared.

No examples provided.

runsec_list_skills ~34

List RunSec security skills (language/framework packs) with activation triggers, extensions, and pattern counts for remediation routing.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

runsec_threat_model ~115

STRIDE architectural threat model: analyzes Syft SBOM, package.json, docker-compose, and repo signals. Writes runsec-threat-model.md and .threat-model-cache.json in the workspace.

NameTypeReqDescription
contextstring–Optional free-text context (stack, deployment model, integrations) to refine STRIDE analysis.
project_namestring–Optional project name used to infer architecture profile (kubernetes-api, desktop-gateway, generic).
workspace_pathstringyesAbsolute or relative path to repository root.

No output schema declared.

No examples provided.

runsec_update_threat_model ~125

Save IDE-agent STRIDE threat model to <workspace>/.runsec-cache/threat-model.json for reuse on the next audit (delta-oriented Step 2 in agent contract).

NameTypeReqDescription
profilestring–Optional architecture profile label (e.g. kubernetes-api, generic).
scope_filesarray–Optional relative paths covered by this threat model revision.
threat_model_markdownstringyesFull or delta-merged STRIDE threat model markdown produced by the IDE agent.
workspace_pathstringyesAbsolute or relative path to repository root.

No output schema declared.

No examples provided.

submit_agent_findings ~231

Canonical findings store + Hub sync (user intent: @runsec verify and sync). Default: merge by id (partial submits update only listed findings; others preserved). Use replace_all:true for full audit terminal submit. Remove fixed items via resolved_ids or finding resolution: resolved|false_positive. verification_status enum is strict; poc_output is mandatory on upserts.

NameTypeReqDescription
findingsarrayyesStructured findings only — server renders Markdown. Do not submit pre-formatted report text.
is_new_auditboolean–Set true on the first submit after runsec_audit_* to force replace_all (clears ghost findings from prior audits).
replace_allboolean–When true, incoming findings replace the entire cache (minus resolved_ids). Default false: merge by id. Auto-enabled when static audit is newer than last agent sync.
resolved_idsarray–Finding ids to remove from cache (fixed/false positive). Use with partial verify submits; omit ids you want to keep unchanged.
workspace_pathstringyesRepository root where runsec-report.md will be updated.

No output schema declared.

No examples provided.

Common questions

What is the io.github.runsec-io/mcp server?

io.github.runsec-io/mcp is listed in the public MCP registry as io.github.runsec-io/mcp. RunSec MCP server for workspace security scanning and remediation workflows. This page covers its npm package (@runsec/mcp).

Is the io.github.runsec-io/mcp server safe to use?

io.github.runsec-io/mcp scores 75 out of 100 on VerifyMCP. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.runsec-io/mcp server expose?

io.github.runsec-io/mcp exposes 19 tools: runsec_audit_owasp, runsec_audit_pcidss, runsec_audit_soc2, runsec_audit_hipaa, runsec_audit_general, and 14 more. Their descriptions and schemas cost roughly 2,352 tokens of context every time the server is loaded.

Is the io.github.runsec-io/mcp server still maintained?

io.github.runsec-io/mcp is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.runsec-io/mcp server under?

io.github.runsec-io/mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.