"namespace:io.github.mgleonard-ops" matching MCP tools:

• agent_operators_set

  fomox402 — Last-Bidder-Wins on Solana

  Mutate the operator whitelist with an owner-signed payload. WHAT IT DOES: POSTs /v1/agents/:agent_wallet/operators with { payload, signature }. Broker enforces that the signer is the OWNER (agent_wallet itself) — operator-signed mutations of the whitelist are rejected even if the signer is otherwise authorised to write configs. Headless — the broker NEVER signs. WHEN TO USE: granting / revoking write access for a sidecar process, rotating an operator key, or wiping the whitelist before retiring an agent. OPS: add — append `operator` to the list (idempotent on existing entry) remove — drop `operator` from the list (idempotent on missing entry) set — replace the entire list with `operators` (use [] to wipe) PAYLOAD CANONICALISATION: broker re-stringifies `payload` with sorted keys and no whitespace before verifying the signature. Sign that exact form. RETURNS: OperatorsList after the mutation. FAILURE MODES: operators_set_failed (bad_signature) — payload != signed bytes operators_set_failed (signer_not_owner) — only the owner may mutate the list operators_set_failed (payload_expired) — broker 410 operators_set_failed (nonce_replayed) — duplicate nonce RELATED: agent_operators_list (read), agent_equip_set (the permission you're granting).

  Connector

• agent_operators_set

  fomox402

  Mutate the operator whitelist with an owner-signed payload. WHAT IT DOES: POSTs /v1/agents/:agent_wallet/operators with { payload, signature }. Broker enforces that the signer is the OWNER (agent_wallet itself) — operator-signed mutations of the whitelist are rejected even if the signer is otherwise authorised to write configs. Headless — the broker NEVER signs. WHEN TO USE: granting / revoking write access for a sidecar process, rotating an operator key, or wiping the whitelist before retiring an agent. OPS: add — append `operator` to the list (idempotent on existing entry) remove — drop `operator` from the list (idempotent on missing entry) set — replace the entire list with `operators` (use [] to wipe) PAYLOAD CANONICALISATION: broker re-stringifies `payload` with sorted keys and no whitespace before verifying the signature. Sign that exact form. RETURNS: OperatorsList after the mutation. FAILURE MODES: operators_set_failed (bad_signature) — payload != signed bytes operators_set_failed (signer_not_owner) — only the owner may mutate the list operators_set_failed (payload_expired) — broker 410 operators_set_failed (nonce_replayed) — duplicate nonce RELATED: agent_operators_list (read), agent_equip_set (the permission you're granting).

  Connector

• send_message

  Dock

  Send a direct message to another agent or human in the messaging substrate. Wires through cue.dock.svc, the same path the /live UI uses, so the recipient sees this message in their drawer (and, once they have a Dock-connected agent worker running, their agent harness's inbox). Address format is `<agent_slug>@<user_slug>`: `flint@socrates` targets the `flint` agent owned by user `socrates`; `self@<user_slug>` targets a human's synthetic self-agent (use this to message a human directly when you don't know which of their agents to ping). Use this when an agent legitimately needs to ask a teammate (human or agent) for help, hand off work, or follow up async; don't use it as a chat-ops side-channel for things that belong in workspace events. Sender identity follows the caller: agent callers send AS themselves, user callers send AS their self-agent (`self@<their_slug>`). Body cap is 32,000 chars. Returns `{ messageId, threadId, to }` on success. The recipient is resolved against the substrate's identity space, NOT against your accessible workspace set, this is messaging, not workspace write access. Pre-cue.dock.svc-deploy environments return `cue_not_configured` (caller treats as 'messaging not deployed yet').

  Connector

• task

  Fast.io

  Task lists and tasks in workspaces/shares with statuses, priorities, assignees, dependencies, bulk ops. Call action='describe' for the full action/param reference. Destructive: delete-list, delete-task.

  Connector

• pipeworx_feedback

  Epo Ops

  Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.

  Connector

• devloop_record_sandbox

  Keploy

  Record mocks for V1 repo-mode API tests using the V1-native CLI command `keploy sandbox local record`. Runs the dev's app under the keploy eBPF agent, drives the V1 chained-CRUD tests from `keploy/api-tests/<resource>/test.yaml`, captures every outbound call (DB queries, Redis ops, downstream HTTP) as mocks, and lays them out at `<app_dir>/keploy/<suite-name>/{tests/, mocks.yaml, config.yaml}` in the standard OSS test-set tree. On success, mocks upload to the Keploy canonical pool by content hash; the hash lands in config.yaml so a teammate's later replay fetches the same bytes. CRITICAL — DO NOT CONFUSE WITH `keploy record sandbox`: * `keploy sandbox local record` (V1, repo-mode) ← this is what the playbook below uses * `keploy record sandbox` (legacy, cloud-mode) ← DO NOT call this for V1 The two are entirely different commands. Cloud-mode requires server-side suites (queried via --suite-ids) — V1 repo-mode reads tests from the local filesystem and never registers them in the cloud. If the dev is in repo storage mode (verify via devloop_resolve_storage's source=persisted, mode=repo), V1 is the ONLY correct sandbox path. STRICT — TIME-FREEZING DOES NOT APPLY TO RECORD. Recording MUST use the dev's regular (prod) Dockerfile or native binary. NEVER spawn the app via Dockerfile.keploy / "-f docker-compose.keploy.yml" / "-tags=faketime" build during record. The faketime binary writes wrong timestamps into captured mocks (it reads time from the offset file, not the wall clock) and the entire capture becomes corrupt — recovery requires re-recording from scratch with the prod binary. If a previous replay failed with expired-JWT and the dev wants to "fix" it, the fix is to re-RUN the replay with --freezeTime, NOT to re-record. The recorded mocks captured against the prod binary are exactly what replay's clock-rewind is designed to validate; touching the record path defeats the whole mechanism. ONLY call this with an explicit dev opt-in. The valid triggers: * Dev directly asks ("capture mocks", "sandbox record", "rerecord the users mocks"). * Post-resource menu (Step 5 of devloop_generate_resource_flow) — dev picks "Capture mocks so CI runs in seconds". * get_session_report shows mock_mismatch_dominant=true AND the dev says yes to your "rerecord?" prompt. Pre-conditions: * Dev's app must NOT already be running (keploy spawns its own copy of the app under the agent's eBPF hooks via the -c command). If a server is up at the target port, KILL IT first or the agent's network capture won't see the traffic. * Real downstream deps (MySQL, Redis, Kafka, etc.) MUST be running — the capture proxies through to them on first contact so the recorded mocks contain real responses. * The test YAML must exist at <app_dir>/keploy/api-tests/<resource>/test.yaml. Returns a playbook for `keploy sandbox local record` with the V1 flag surface: --test-dir, --app-url, -c (spawn command), --container-name (docker-compose only), --skip-mock-upload (offline), --skip-report-upload (offline). Mocks land per-suite at keploy/<suite-name>/. NDJSON progress at --progress-file for the standard tail-til-done loop.

  Connector

• update_mnemons_content

  argo-mcp

  Edit the content blocks of one or more mnemon entries. Each item carries an entryId and an ordered list of ops (append, insertAfter, replace, remove) applied atomically per entry. Block addressing: get block ids from get_mnemon, then target them in replace/remove/insertAfter. New blocks (append, insertAfter, replace) get fresh server-generated UUIDs. Text in block 'text' is HTML — use <b>, <i>, <a>, <br>, <img>; do NOT use Markdown like '**bold**' or '# heading'. Use blockType for paragraph/heading1/heading2/bullet_list/numbered_list/todo/quote/code/callout/divider/image. Inline <img src="data:..."> or <img src="https://..."> is uploaded to the campaign asset bucket and the src is rewritten to asset:<id>. SSRF-blocked / oversize / failed fetches are stripped with a warning. On a bad op (missing blockId, unknown blockType, etc.) the whole entry's batch is rejected with the failedOpIndex; no partial mutation per entry.

  Connector

• emem_cell_geojson

  emem — Earth memory protocol

  Cell polygon as a native MCP EmbeddedResource (mimeType application/geo+json). Properties carry centre lat/lng, bbox, approx size in metres, and the 8-cell neighbourhood — drop straight into Mapbox / Leaflet / Deck.gl / QGIS without a GIS pipeline. When to use: Call when the agent (or a downstream renderer) needs the cell as geographic geometry — for map overlays, polygon-clipping ops, or feeding a styling pipeline. Pass `cell` as cell64 or place name. The result is a GeoJSON Feature with Polygon geometry; for a FeatureCollection that includes every recalled fact's value as a property, fetch /v1/cells/{cell64}/recall_geojson?bands=... over plain REST instead.

  Connector

• compare_products

  PricePilot — Free CPG Pricing Intelligence

  Compare multiple product prices against an Amazon CPG category's peers. Use when a multi-channel CPG brand needs to stack-rank their SKUs — e.g. identifying which SKUs are underpriced relative to Amazon peers, flagging products where the Amazon Buy Box sits materially below the retail MSRP, or building a cross-channel price-audit table for an ops review. Replaces manual store walks and spreadsheet comparisons. Returns: comparisons (list, per product: name, price, percentile_rank, position, vs_median), category, category_trend, sample_size, last_refreshed, cta. Args: products: List of items, each a dict with 'name' (string) and 'price' (number in dollars). Minimum 1 item; 3-20 is the useful range. category: Exact category name — Grocery & Gourmet Food, Health & Beauty, Household, or Pet Supplies. Case-insensitive.

  Connector

• polymarket_arbitrage

  Epo Ops

  Find arbitrage opportunities on Polymarket by checking for monotonicity violations across related markets. TWO MODES: (1) `event` — pass a single Polymarket event slug; walks that event's child markets and checks ordering within it. (2) `topic` — pass a topic / seed question (e.g. "Strait of Hormuz traffic returns to normal"); the tool searches across separate events for related markets, groups them, then checks monotonicity. Cross-event mode catches the cases where Polymarket lists each cutoff as its own event ("…by May 31" is event A, "…by Jun 30" is event B — single-event mode misses the May≤June rule). Returns ranked opportunities with suggested trade direction + reasoning.

  Connector

• recall

  Epo Ops

  Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlier — the user's target ticker, an address, prior research notes — without re-deriving it from scratch. Scoped to your identifier (anonymous IP, BYO key hash, or account ID). Pair with remember to save, forget to delete.

  Connector

• compare_entities

  Epo Ops

  Compare 2–5 companies (or drugs) side by side in one call. Use when a user says "compare X and Y", "X vs Y", "how do X, Y, Z stack up", "which is bigger", or wants tables/rankings of revenue / net income / cash / debt across companies — or adverse events / approvals / trials across drugs. type="company": pulls revenue, net income, cash, long-term debt from SEC EDGAR/XBRL for tickers like AAPL, MSFT, GOOGL. type="drug": pulls adverse-event report counts (FAERS), FDA approval counts, active trial counts. Returns paired data + pipeworx:// citation URIs. Replaces 8–15 sequential agent calls.

  Connector

• list_skills

  Hatchable

  List the registry of platform skills — discrete how-to guides for one specific task each (e.g. 'gate-an-endpoint', 'add-a-cron-job', 'add-rag-search'). Each entry is a name, one-line purpose, and category. Use this to find the right skill, then call `read_skill(name)` to load the full pattern. When in doubt about how a Hatchable feature works, **list_skills first**. The skills are the canonical, agent-tested patterns. They beat guessing or reading the verbose docs. Filter by `query` (matches name + purpose) or `tag` (auth, data, ai, ops, etc.). Without filters, returns the full registry (~35 entries).

  Connector

• discover_tools

  Epo Ops

  Find tools by describing the data or task. Use when you need to browse, search, look up, or discover what tools exist for: SEC filings, financials, revenue, profit, FDA drugs, adverse events, FRED economic data, Census demographics, BLS jobs/unemployment/inflation, ATTOM real estate, ClinicalTrials, USPTO patents, weather, news, crypto, stocks. Returns the top-N most relevant tools with names + descriptions. Call this FIRST when you have many tools available and want to see the option set (not just one answer).

  Connector

• bet_research

  Epo Ops

  Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet (crypto price / Fed rate / geopolitical / sports / corporate / drug approval / election / other), fans out to the right packs (e.g. crypto+fred+gdelt for a BTC bet, fred+bls for a Fed bet, gdelt+acled+comtrade for Strait of Hormuz), and returns an evidence packet plus a simple market-vs-model comparison so the caller can see where the implied probability disagrees with the data. Use for "should I bet on X?", "what does the data say about this Polymarket market?", or "is there edge in this bet?". This is the core demo product — agents that get bet-relevant context here convert better than ones that have to discover the packs themselves.

  Connector

• entity_profile

  Epo Ops

  Get everything about a company in one call. Use when a user asks "tell me about X", "give me a profile of Acme", "what do you know about Apple", "research Microsoft", "brief me on Tesla", or you'd otherwise need to call 10+ pack tools across SEC EDGAR, SEC XBRL, USPTO, news, and GLEIF. Returns recent SEC filings, latest revenue/net income/cash position fundamentals, USPTO patents matched by assignee, recent news mentions, and the LEI (legal entity identifier) — all with pipeworx:// citation URIs. Pass a ticker like "AAPL" or zero-padded CIK like "0000320193".

  Connector

• remember

  Epo Ops

  Save data the agent will need to reuse later — across this conversation or across sessions. Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject) so you don't have to look it up again. Stored as a key-value pair scoped by your identifier. Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours. Pair with recall to retrieve later, forget to delete.

  Connector

• get_category_trend

  PricePilot — Free CPG Pricing Intelligence

  Report the 30-day Amazon price-trend direction for a CPG category. Use when a pricing ops lead asks whether category pricing is rising, stable, or falling — e.g. setting retail promo calendar against an Amazon backdrop, deciding whether to raise wholesale prices during inflationary windows, or catching a price war before it spills into their channel. Returns: trend_direction (Rising / Stable / Falling / Insufficient Data), trend_window ("30 days"), confidence (note with product count), category (resolved name), last_refreshed, cta. Args: category: Exact category name — Grocery & Gourmet Food, Health & Beauty, Household, or Pet Supplies. Case-insensitive.

  Connector

• recent_changes

  Epo Ops

  What's new with a company in the last N days/months? Use when a user asks "what's happening with X?", "any updates on Y?", "what changed recently at Acme?", "brief me on what happened with Microsoft this quarter", "news on Apple this month", or you're monitoring for changes. Fans out to SEC EDGAR (recent filings), GDELT (news mentions in window), and USPTO (patents granted) in parallel. since accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes + total_changes count + pipeworx:// citation URIs.

  Connector

• pg_classified_keyword_match

  predictionguard

  Daily compliance triage: scans top Polymarket markets by 24h volume and flags those whose question text matches curated sensitive-keyword categories — military action, regime change, leadership death, diplomacy, intelligence ops, monetary policy, regulatory action. Returns flagged markets with monitoring severity (HIGH/MEDIUM/LOW), matched categories and keywords, and volume. Pair flagged HIGH markets with pg_insider_signal_scan for active surveillance.

  Connector