Skip to main content
Glama
615,958 tools. Updated 2026-09-27 11:02

"How to access the BASH shell" matching MCP tools:

  • Returns turva.dev's engagement principles: async-only, least access, the result shows up in scanner numbers, and open and verifiable. Use this when a user asks how turva.dev works with clients or what rules an engagement follows. For what is sold and what it costs use get_services instead, and for how to start use get_contact. Read-only: returns static JSON that is compiled into the Worker, so it changes nothing and updates only on deploy.
    ConnectorNo auth
  • Inspect the files of an EXISTING artifact: list them, search their text, read them, or review the commit history. Works with no shell, no git and no network access, so prefer it whenever you cannot run git. Pass the sessionId (the last path segment of a .../chat/<sessionId> URL). A canvasDraft field, when authorized, reports an uncommitted Canvas draft. Use action draft to inspect its projection overlay explicitly; ordinary reads remain committed files. Draft access requires write permission. Typical flow to change something: action "search" to find the file, action "read" for the files you will edit, then artifact-edit. Every response includes "revision", the artifact's current commit — pass it back as artifact-edit's baseRevision. Use action "read" with a "revision" to see how a file looked at an earlier commit (this is how you undo something). Assets — images, fonts, media — are readable too: action "read" answers with size, mime and oid under "asset": true whenever a file's bytes are not text, instead of content. That check is on the bytes, so it is the authority: an SVG reads as text, and a file with an unfamiliar extension may still come back as an asset. When a search comes back empty, check "notSearched": "assets" counts binary files a text query can never match, and "excluded" counts files under node_modules, dist or build — re-run with includeExcluded true to search those. A "tree" listing also maps any path artifact-edit cannot change under "unwritable". For generation or build progress use artifact-status instead; this shows the commit log, not build state.
    ConnectorOAuth
  • Fetch the full record for a urn:air: identifier returned by search_registry: endpoint, description, publisher, conformance grade, and trust level. Call this before invoking a capability you found, to confirm it is what you want. Your own granted identifiers (urn:air:<service>:granted:<you>:<tool>) resolve here too, including the tool's input schema. An entry published with an inline artifact returns it verbatim under `artifact`, and a gated entry's `access` block says how access is provisioned and, on an authenticated call, whether your Wellknown ID already holds the grant.
    ConnectorNo auth
  • Generate an audit-ready agent-governance policy for a fleet. PREMIUM (license). Covers inventory cadence, ownership rules, least-privilege approval gates, injection defense, logging/retention, and decommissioning triggers. Typical input {"fleet_context": "20 agents, 3 with shell access, one finance bot"} returns {"policy": ..., "sections": {...}, "context_note": ..., "audit_checklist": ["...", ...]}. Use when a fleet needs a written policy document. Not for assessing what the fleet currently does (inventory_report, audit_mcp_config). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
    ConnectorNo auth
  • Generate an audit-ready agent-governance policy for a fleet. PREMIUM (license). Covers inventory cadence, ownership rules, least-privilege approval gates, injection defense, logging/retention, and decommissioning triggers. Typical input {"fleet_context": "20 agents, 3 with shell access, one finance bot"} returns {"policy": ..., "sections": {...}, "context_note": ..., "audit_checklist": ["...", ...]}. Use when a fleet needs a written policy document. Not for assessing what the fleet currently does (inventory_report, audit_mcp_config). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
    ConnectorNo auth
  • Returns instructions for creating a DPF account, verifying its email, resending the verification code, or resetting a forgotten password — it never performs these itself and never asks for a password. A password typed into this chat would sit in the conversation transcript, so every action instead returns the DPF website's own form, or a curl command that reads the password from a shell variable the user sets themselves in their own terminal. Hand the command to the user to run — do not run it yourself even if you have shell access, since composing the export line would require seeing the password. action "register": requires email, firstName, lastName, and termsAccepted: true (only after the user has explicitly agreed to the DPF Terms of Service and Privacy Policy in this conversation). action "verify": confirm the 6-digit code DPF emailed after registration (requires otp). action "resend": re-send that code if it never arrived. action "forgot-password": request a password-reset code (requires email). action "reset-password": submit that code and set a new password (requires otp).
    ConnectorOAuth

Matching MCP Servers

  • A
    license
    A
    quality
    C
    maintenance
    Enables execution of bash commands via MCP, allowing clients to run shell commands and set a working directory.
    2
    34
    MIT
  • A
    license
    B
    quality
    F
    maintenance
    A secure server that enables AI applications to execute shell commands in specified directories, supporting multiple shell types (bash, sh, cmd, powershell) with built-in security features like directory isolation and timeout control.
    1
    21
    Apache 2.0

Matching MCP Connectors

  • No arguments. Returns how many MCP servers have been read at source level, and the share of them with each category of finding (credential access, network egress, install-time execution, prompt-injection surface). Use this to judge whether checking a specific server is worth it before you look one up. It reports aggregate counts only - no per-server findings, and no verdict about any individual server.
    ConnectorNo auth
  • Returns who runs turva.dev and the official ways to reach it: the operator and business details, the email address, the Signal link, the LinkedIn profile, the correspondence languages, the first-reply time and the access an audit needs. Use this when a user asks who is behind turva.dev, how to contact it, how to start an audit or what access has to be granted. For what is sold and what it costs use get_services instead. Read-only: returns static JSON that is compiled into the Worker, so it changes nothing and updates only on deploy.
    ConnectorNo auth
  • Send a keycode to a device. Accepts numeric keycode OR named key (HOME, BACK, ENTER, VOLUME_UP, VOLUME_DOWN, POWER, APP_SWITCH, ESCAPE, DELETE, TAB, SEARCH, MENU). System-policy keys (APP_SWITCH/187, MENU/82, POWER/26) are always sent via shell — they require policy-level handling that the control channel cannot reach. Other keys try the control channel first and fall back to shell on error/timeout. Every route here is injected — this tool has no kernel input path. Use device_uhid_key_press instead when the target app filters or ignores injected key events and the press has to land as real kernel input.
    ConnectorOAuth
  • Run bash on the same remote sandbox as FLOWRA_JS_REMOTE_WORKBENCH for this session.id. Files under /home/user/files stay between calls. The shell itself starts fresh each time. With session.id and useWorkbenchSnapshot (default true), the latest FLOWRA_MULTI_EXECUTE_TOOL snapshot is at /home/user/files/multi_execute.json (also FLOWRA_WORKBENCH_JSON). That snapshot only exists if the earlier call set syncResponseToWorkbench: true. For bulk JavaScript and run_tool loops prefer FLOWRA_JS_REMOTE_WORKBENCH. Do not call FLOWRA_MULTI_EXECUTE_TOOL from inside bash.
    ConnectorAPI key
  • Built-in product help — ask a natural-language "how do I…" question about Fastio and get a grounded, product-aware answer (or a short clarifying question) back in one call. EXPLAIN-ONLY / ADVISORY: it returns GUIDANCE TEXT and performs NO platform action (it will not create shares, move files, or change anything) — read the guidance, then act with the other tools. Answers are grounded in Fastio's own how-to knowledge AND phrased in terms of these MCP tools — they name the concrete `<tool> action="…"` calls to make — so prefer this over guessing endpoints or burning exploratory calls. For Q&A over YOUR uploaded files (RAG) use the `ai` tool instead — `how-to` answers questions about Fastio ITSELF. FREE and requires only an authenticated user (no org, no plan gate, no billing). Call action='describe' for the full action/param reference.
    ConnectorNo auth
  • Pull down the notification panel, the Quick Settings panel, or collapse open panels. action="notifications": pull down the first panel (notifications). action="settings": pull down Quick Settings (some OEMs require notifications first). action="collapse": close any open panel. Tries control channel first; falls back to `cmd statusbar` shell on error. Returns { ok, action, transport }.
    ConnectorOAuth
  • How far an access role's agents may reach into one mailbox: the access level (write = everything its capabilities allow, read = search and read only, none = hidden), which folders its file tools may use (all / only these / all except these, by folder path), and which calendars (all / only these / all except these, by calendar name). Give only the parts you want to change; the others stay as they are. list_access_roles shows the current standing. This only stages a request: the owner opens the link in their browser, reviews it, and approves it there with their agent PIN. Never ask for or accept the PIN in chat.
    ConnectorOAuth
  • Scan source code for injection vulnerabilities: SQL injection, command injection, path traversal via unsafe string concatenation/unsanitized input. Supports Python, JavaScript, TypeScript, Java, Go, Ruby, Shell, Bash. Use to detect input-handling bugs; for secrets use check_secrets. Companion code-security tools: check_secrets (hard-coded credential detection), check_dependencies (known-CVE vulnerability audit), check_headers (live HTTP security-header validation), scan_headers (live HTTP scan via domain). Free: 30/hr, Pro: 500/hr. Returns {total, by_severity, findings}. No data stored.
    ConnectorNo auth
  • PRIMARY path to close a Grove goal: this is the ONLY tool that covers an acceptance criterion. Attach binary evidence (screenshot, log dump, API response, export) to an AC — call it once per criterion to satisfy the close gate. The subordinate goal-add-evidence-text only adds context for proofs with NO bytes (URLs to permanent external sources, manual repro descriptions) and does NOT cover an AC. Caption is optional but strongly recommended: state what the file captures and the reproduction conditions (URL/commit/session/inputs) so a third reviewer can reproduce. ⚠ PICK THE RIGHT TRANSPORT BEFORE YOU CALL THIS TOOL ⚠ • BEST for ANY file > ~1 KB raw — and the ONLY no-token path, so use it in a claude.ai / hosted-agent session that has no raw X-Auth-Token → call the sibling MCP tool `goal-request-upload` with this same criterionId. It returns a one-time {uploadUrl, expiresAt}; then stream the raw bytes with a single PUT: `curl -sS --fail --upload-file "/abs/path/to/file.png" "<uploadUrl>"` (optionally add -H "X-Content-Sha256: <hex sha256>" so corruption fails fast). No base64, no token — the signed ?t= ticket in the URL is the only credential, single-use, criterion-scoped. The PUT response is the same evidence JSON this tool returns. • ALTERNATIVELY, if you DO have the raw X-Auth-Token in your shell → the `planner-attach.sh` helper (zero-install bash, binary-safe). The MCP base64 path below is unreliable for non-trivial files: long string arguments get truncated or whitespace-corrupted on the agent side BEFORE the JSON-RPC request is sent. Measured 2026-05-20 on prod: a 4 KB PNG arrived at the server as 1874 decoded bytes (file_hash_mismatch); a 2 KB payload arrived with stray whitespace (failed base64_decode). The server itself accepts up to 25 MiB raw — the bottleneck is the agent-side serialisation of contentBase64, NOT the server. planner-attach.sh COPY-PASTE RECIPE (replace 3 placeholders, run in your shell): curl -sS https://planner.monopoly-gold.com/api/cli/planner-attach.sh \ | PLANNER_TOKEN="<same X-Auth-Token you use for MCP>" bash -s -- \ --criterion-id "<CRITERION_UUID>" \ --file "/abs/path/to/file.png" \ --caption "what is captured and the repro conditions" \ --created-by "<your agent id>" Where to get each value: - PLANNER_TOKEN: the very same token that is already in your MCP config under the X-Auth-Token header for the `planner` server. NOT a separate credential. - CRITERION_UUID: the AC id you got from goal-get / goal-list. Same UUID you would pass to this MCP tool. - file path: absolute path on YOUR (agent) machine — the script reads it locally and streams multipart. The planner server never sees your filesystem. The helper computes SHA-256 itself and ships it as `contentSha256`, so any in-flight corruption fails fast with HTTP 400 instead of poisoning the evidence row. Output on stdout is the same JSON shape this MCP tool returns; non-zero exit means HTTP ≥ 400 (stderr explains). Without curl/bash? Fall back to raw multipart: POST https://planner.monopoly-gold.com/api/criteria/<id>/evidence/file, header X-Auth-Token, form fields file=@..., contentSha256=..., caption, createdBy. • File ≤ ~1 KB raw → this MCP tool is fine. ALWAYS pass `contentSha256` (hex SHA-256 of raw bytes BEFORE base64). Without it, a silently truncated PNG looks valid to the MIME sniffer; the server cannot distinguish a truncated 4 KB PNG from a valid 1 KB one and the vision judge burns ~30s on broken bytes. With the hash, the server fast-fails with error=file_hash_mismatch and points back here at the multipart endpoint. Validates MIME whitelist (png/jpeg/webp/gif/mp4/pdf/txt/json/zip), per-file size cap (ATTACHMENTS_MAX_FILE_BYTES, default 25 MiB), per-project attachments quota. Returns evidence record + file URL + serverSha256.
    ConnectorNo auth
  • PREFERRED tool for sending work to an AI agent. Dispatches a task to the agent's inbox — picked up and executed automatically. No list ID needed. REQUIRES the agent:dispatch permission on this connection (CODE:/SHELL: tasks also require agent:dispatch:code) — reconnect and tick the agent checkbox(es) if refused. Routing is by TITLE PREFIX only: CODE: SHELL: PLAN: MCP: → local Claude Code on Mike's PC; RESEARCH: WRITE: REVIEW: → cloud; no prefix (DEFAULT) → local while the PC agent is alive, else cloud. The cloud agent refuses CODE/SHELL/PLAN/MCP. Use "agent" param to target a specific agent (default: claude-code-local). Use tascan_list_agents to discover available agents; track progress with tascan_get_task (its "agent" block).
    ConnectorNo auth
  • Revoke a third-party app's access to the user's Agentcard account. Disconnects the app and invalidates its OAuth tokens; it must reconnect via OAuth to regain access. Pass the clientId shown by list_connections.
    Connector
    Destructive
    No auth
  • Walk the guided path to build a nifra app end to end - an ORDERED sequence (create → page route → loader → typed API → typed client → auth → background jobs → deploy), not the random-access search of nifra_docs/nifra_example. Call with no args for the step index; pass `step: N` for that step's goal, how to do it (which tool emits the correct artifact), and how to verify it. Use it when scaffolding a new app or learning nifra's flow - each step composes the other nifra_* tools.
    ConnectorNo auth
  • Get git access to an EXISTING artifact, for local development with a real git client. Use this when you HAVE a working shell with git and outbound network access AND the job suits a local checkout — a large refactor, running or testing the project, branches, or history rewriting. For ordinary reading and editing of an artifact’s files, prefer artifact-explore and artifact-edit: they need no shell, no git and no network of your own, and they change the same repository. An artifact is a real git repository. Pass the sessionId — the id of an existing artifact (e.g. the last path segment of a .../chat/<sessionId> URL, like "mr25vsjppVtbMx") — and this returns a gitRemoteUrl plus the authenticated principal’s commitAuthor. After cloning, apply the returned `git config user.name` and `user.email` instructions before committing; then edit files, commit, and `git push` — pushing updates the live artifact. The gitRemoteUrl holds a short-lived access token scoped to this one artifact (read-only or read-write, depending on your access). Tokens CANNOT be renewed: on a "token expired" git error, call this tool again for a fresh gitRemoteUrl and run `git remote set-url origin <new gitRemoteUrl>`, then retry. If a git command instead fails because the host cannot resolve or reach the server (DNS, proxy or firewall errors), do NOT retry it — that environment has no route to the git remote, so use artifact-edit instead. Treat the gitRemoteUrl as a secret. To rename an artifact or change its visibility, use artifact-update_metadata.
    ConnectorOAuth
  • SAFETY / OVERSIGHT CHECK before a dangerous or destructive action (shell command, file deletion, DB statement, network call). Call this to have VITNA check the action BEFORE you run it: it flags dangerous shell / SQL / secret-exfil / prompt-injection / suspicious-network patterns and returns { decision: allowed|blocked|flagged }. RESPONSE SHAPE DEPENDS ON THE KEY: an unclaimed trial key gets the decision label only, because the pattern detail is what makes the classifier worth stealing. A claimed key additionally gets threat_category, severity, reason (the rule names that matched, never the matched text), a threats[] array and a redacted echo of what was scanned, plus a signed audit record the user can review. VITNA evaluates and records; it does NOT enforce, so treat blocked / flagged as a stop and get human approval. This is how a user keeps you in check. Heuristic pattern match, not a sandbox: novel or obfuscated payloads can pass.
    ConnectorNo auth
  • List spaces the user can see (their own/member spaces + public ones), each annotated with THIS caller's permission so you know what they may do: - your_role: 'owner' | 'editor' | 'viewer' | null (their space membership) - is_owner: they own the space - access: 'owner' | 'member' | 'public' (how it's available to them) - can_write: their space role permits ingest (owner/editor) — a real ingest also needs the 'ingest' capability + any per-space access rules. Use this to tell the user which spaces they can read vs. write vs. only see as public.
    ConnectorNo auth