Skip to main content
Glama
650,522 tools. Updated 2026-10-14 04:01

"Session" matching MCP tools:

  • sessionA

    VaayaA

    Run a command or code in an open E2B sandbox session (started by `use` with action `create_session`, which returns a `session_id`). Pass `session_id` plus either `command` (a shell command) or `code` (+ optional `language`: python/javascript/bash). Returns stdout/stderr/exit_code (or the code result). The sandbox stays alive — and billed per second of uptime — until you `close` it; re-running reuses the SAME box, so filesystem + process state persist between calls. ALWAYS `close` when done.
    ConnectorNo auth

  • sessionB

    AnwaniA

    Check that Anwani is connected for this user. Does not return internal IDs.
    ConnectorNo auth

  • session

    ContextStreamB

    Session and memory management — NOT for codebase/file search (use `search`). LESSONS: on a mistake or correction call action='capture_lesson', not local files. DECISIONS: action='capture', event_type='decision'. PAST SESSIONS: `context()` surfaces `[GROUNDING]`; when it is fresh and sufficient, do not immediately call action='recall'. Use recall as the first explicit escalation when grounding is absent, thin, stale, off-topic, or the user asks for history. smart_search searches MEMORY only, not code. RESUME earlier work: action='resume' or 'resume_list', session_id = id init returned. PLANS: action='capture_plan' (structured steps; creates linked tasks by default); do not use action='capture' for plans. Snapshots: action='capture', event_type='session_snapshot'. Daily Recaps run around 23:00 user time, not at MCP session boundaries. Also: ground, retro_capture, user_context, list_suggested_rules, suggested_rule_action, suggested_rules_stats, set_account_mode. Full reference: the `action` parameter.
    Connector
    Destructive
    OAuth

  • update-sessionA

    Music StudioA

    Only for a live session. Swaps new code into the session's player while the music keeps playing. Send the WHOLE pattern, as for play-live-pattern. It lands on the next bar (quantize 1, the default), the next multiple of n bars, or at once (0): set quantize to your phrase length (8-bar phrase → 8). If the player answers within a few seconds, the result says whether it ran the code, or its error. To change a piece's remember() state, ship a merge, not a new start value (get-strudel-guide topic 'interactive').
    ConnectorNo auth

  • get-sessionA

    Music StudioA

    Only for a live session (play-live-pattern session: true). Reads whether the player is up and what it played, its errors and silences, and what the human did since your last read: taps, changes to remember() state, code they ran, a Pass to you, or End. Read it before assuming a piece played. With wait: 'pass' it listens until the human presses Pass, so a whole back-and-forth set fits in one turn: update-session, get-session(wait: 'pass'), answer, listen again.
    ConnectorNo auth

  • get-sessionA

    RoundtableA

    Get full details of a previous MCP session by ID. Returns the complete result including participant responses and moderator synthesis. Use list-sessions first to find session IDs.
    ConnectorNo auth

Matching MCP Servers

  • session-watcher

    nomadop
    A
    license
    A
    quality
    B
    maintenance
    Session Watcher treats your prompt cache as inventory — it uses EOQ theory to tell you whether the current context is still worth carrying, and when to restart. Works with any session-based coding agent.
    3
    20 npm
    5
    MIT

  • session-bridge

    ralskwo
    F
    license
    A
    quality
    B
    maintenance
    Enables selecting a saved Codex or Claude Code session from the same PC and importing its recent context into the other tool, so work can continue across clients with source and omission information.
    3
    -

Matching MCP Connectors

  • Session ReplayOAuth

    Read and triage bug reports captured by Session Replay for your verified domains.

  • Session Replay MCPOAuth

    MCP for retrieving information about recorded session replays.

  • create-checkout-sessionA

    SimFuse eSIM StorefrontA

    Open a checkout session for one or more eSIM plans at frozen prices, using the plan ids that plan-trip, list-plans or get-plan returned. Use it once the traveller has chosen what to buy. It CHARGES NOTHING and reserves no stock: it prices the basket, freezes those prices until the session's price_locked_until, and hands back the session plus a bearer agent key. Payment, completion and cancellation happen afterwards over the SimFuse agentic HTTP API with that key, as the session's `note` explains, and the eSIM is delivered by email once payment settles. Each call opens a NEW session and mints a NEW key, so call it once per basket rather than retrying it to re-read one.
    ConnectorNo auth

  • get-workout-history-session-toolA

    JotiA

    Get full detail (sets, PBs, milestones achieved) for one completed workout session, by id. Use list_workout_history to find ids.
    ConnectorOAuth

  • get-manual-session-detailsA

    TestChimpB

    Fetch a manual test session by id. Returns project id, title, environment, steps (playwright commands, signed screenshot URLs, notes), and linked scenario ordinal ids. Use when authoring a SmartTest from a recorded manual session.
    ConnectorAPI key

  • agent-os-session

    Studocu

    Use this proof tool to verify that the Agent OS MCP server received a valid delegated Studocu session.
    ConnectorNo auth

  • vault-get-session

    mcp-serverA

    [Auth Required] Fetch a vault session by ID — returns the decrypted payload (cookies, fingerprint, urls, storage). Agent access follows owner+privacy rules.
    ConnectorNo auth

  • vault-create-session

    mcp-serverA

    [Auth Required] Create a new vault session under the agent's owner. The payload envelope is { fingerprint?, cookies?, localStorage?, sessionStorage?, urls?, collectedAt? }.
    ConnectorNo auth

  • vault-update-session

    mcp-serverA

    [Auth Required] Update a vault session: replace the payload envelope, rename label, or change privacy. A revision is snapshotted automatically before the update.
    ConnectorNo auth

  • vault-clone-session

    mcp-serverA

    [Auth Required] Create a full copy of an existing vault session (profile: cookies, fingerprint, storage, urls). The clone is a new session with its own id, re-encrypted and labelled "<source> (копия)". Agent access follows the owner+privacy rules.
    ConnectorNo auth

  • vault-revert-session

    mcp-serverA

    [Auth Required] Revert a vault session to an earlier revision. Current state is snapshotted as a new revision before the revert.
    ConnectorNo auth

  • get_session_usageA

    RoutebaseA

    Return usage metrics for the current MCP session: total tool calls, error count, aggregate duration and response size, per-tool call counts, and session timestamps. Metrics are in-memory and reset when the server restarts or the session goes idle. Use this for what this session has spent; for which toolsets exist at all use list_toolsets.
    ConnectorAPI key

  • session_createA

    AgentPay — trust routing + spend caps for x402 agentsA

    Open a budget-capped agent session on AgentPay. Pay $0.01 USDC once — get a session_id, budget config, and gateway URL. Enforces a hard max_spend cap across all subsequent tool calls via the AgentPay SDK. The entry point for agents discovering AgentPay on Base Bazaar. Use when: You want to start an AgentPay session with a hard spend cap and get a session_id for tracking. Not for: you only need a session for free tools — the SDK's quickstart() opens one at no cost; this call settles $0.01 on-chain. Returns: session_id, max_spend, agent_address, gateway_url, tools_endpoint, created_at, receipt (tx_hash + network) Example response: {"session_id":"f47ac10b-58cc-4372-a567-0e02b2c3d479","max_spend":"0.10","agent_address":"GBCVQCNFWPM3GDO4GPT4YEQ42ZHPY67QTJA3WN5ERQIKQDXKBX62SLNJ","label":null,"gateway_url":"https://agentpay.tools","tools_endpoint":"https://agentpay.tools/tools","created_at":"2026-05-27T12:00:00Z","receipt":{"tx_hash":"0xabc...def","network":"base","amount_usdc":"0.01"},"sdk_hint":"Use `from agentpay import Session` to enforce the max_spend cap client-side."} Price: $0.01 USDC per call (x402 over MCP: an unpaid call returns PaymentRequired; pay via _meta x402/payment)
    ConnectorNo auth

  • __unlock_blockchain_analysis__A

    blockscout-mcp-serverA

    Initializes a Blockscout MCP session: returns server reference data, the `blockscout-analysis` skill pointer, and the URI resolution rule. Call this tool exactly once per session, before any other tool, and reuse its payload for the rest of the session; do not call it again.
    ConnectorOAuth