Skip to main content
Glama
817,998 tools. Updated 2026-11-21 20:58

"A server for finding free and popular resources" matching MCP tools:

  • Discover content franchises within a domain. Two modes: pass `tag` for a precise taxonomy match (every game tagged 'co-op'), or pass `query` for free-text SEMANTIC search powered by pgvector embeddings — finding franchises by meaning ('dark atmospheric games about isolation') even when no literal tag matches. Results are verifiable: tag mode carries tag confidence/corroboration, semantic mode carries a similarity score; both carry entity freshness. When to use: an agent wants a domain-scoped shortlist by tag or by intent. Inputs: a domain plus either a tag or a free-text query.
    ConnectorNo auth
  • Discover content franchises within a domain. Two modes: pass `tag` for a precise taxonomy match (every game tagged 'co-op'), or pass `query` for free-text SEMANTIC search powered by pgvector embeddings — finding franchises by meaning ('dark atmospheric games about isolation') even when no literal tag matches. Results are verifiable: tag mode carries tag confidence/corroboration, semantic mode carries a similarity score; both carry entity freshness. When to use: an agent wants a domain-scoped shortlist by tag or by intent. Inputs: a domain plus either a tag or a free-text query.
    ConnectorNo auth
  • Discover content franchises within a domain. Two modes: pass `tag` for a precise taxonomy match (every game tagged 'co-op'), or pass `query` for free-text SEMANTIC search powered by pgvector embeddings — finding franchises by meaning ('dark atmospheric games about isolation') even when no literal tag matches. Results are verifiable: tag mode carries tag confidence/corroboration, semantic mode carries a similarity score; both carry entity freshness. When to use: an agent wants a domain-scoped shortlist by tag or by intent. Inputs: a domain plus either a tag or a free-text query.
    ConnectorNo auth
  • Returns the plain-language meaning and step-by-step fix for one Malinois finding. Use it while helping the user fix an issue reported by scan_app, or when they ask what a finding means. Pass the rule_id exactly as scan_app returned it. Read-only, no network, instant.
    ConnectorNo auth
  • Maps only stable Tier1 finding identifiers to approved Tier1 services and public resources. Call after a Tier1 score or email-domain check. Do not submit prose, URLs, customer information, or invented identifiers. This tool performs no arbitrary fetching, makes no contact request, changes nothing, and stores nothing.
    ConnectorNo auth
  • Delete ONE AI package resource of a video in one language (eBook, mind map or quiz) — cannot be undone: its content, PDF, images and the published file are removed, also for legacy resources. Same as the dashboard's Remove. Refused while it is still generating (checked before deleting; if that check fails nothing is deleted). Other languages and resources stay. To remove a failed generation card use panda_delete_ai_workflow.
    Connector
    Destructive
    No auth

Matching MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to search, filter, and monitor curated AI model API free credits and low-cost token promotions through eight tools, four resources, and three prompts — including finding deals expiring soon, checking eligibility and blocked conditions, and producing daily briefs.
    MIT

Matching MCP Connectors

  • Human-verified daily catalog of free and cheap AI model API credits and token promos.

  • Your saved places, trips and travel plans — see them, plan days, and add to them from your AI.

  • Uninstall a release and remove the resources it created, including volume data. Use it, not delete_resource, for anything install_template created. Provide the release `name`.
    Connector
    Destructive
    OAuth
  • Free-text search across every public resource family on The Holistic Care (blog articles, mindfulness games, free guided practices, research summaries, glossary terms, public PanchaVikas resources, and podcast episodes). Use this as the general entry point when a request doesn't clearly belong to one specific family — e.g. 'Find something about breathing for anxiety' or 'What has THC published about nondual awareness?'. `resource_type`, `category`, `audience`, `skill`, and `age` are applied as a post-filter over the text search results (the underlying search endpoint only supports free-text query natively), so a narrow combination of filters plus a rare query term can legitimately return few or zero results even if matching resources exist outside the searched batch — for a guaranteed, fully server-side filtered result within one resource family, prefer find_mindfulness_games, find_guided_practices, search_mindfulness_research, lookup_mindfulness_term, or find_podcast_episodes instead.
    ConnectorNo auth
  • Runs the full art-direction review of a project: collisions (frame by frame for films), angles, floating versus resting devices, text overlap, cropping and contrast, composition and color. Use it while building to see every finding, including warnings edit_scene saves anyway; use finish once at the end for the final check, and render_preview to look at the result. Read-only. Every finding has a severity and a fix with ready-to-send edit_scene ops. Returns the findings, errors first, and whether the scene passes.
    ConnectorAPI key
  • Runs the full art-direction review of a project: collisions (frame by frame for films), angles, floating versus resting devices, text overlap, cropping and contrast, composition and color. Use it while building to see every finding, including warnings edit_scene saves anyway; use finish once at the end for the final check, and render_preview to look at the result. Read-only. Every finding has a severity and a fix with ready-to-send edit_scene ops. Returns the findings, errors first, and whether the scene passes.
    ConnectorAPI key
  • ACCOUNT REQUIRED (free, sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead, it works on every tier. Grounded multi-source research across Pipeworx's 2015 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call, this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 7,565 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx, it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass, so multi-step questions resolve in one call. Every finding carries a `hop` field and a citation_uri, a resolvable pipeworx:// record URI, present only when the source emits one that resources/read can actually serve, so a citation you get back is always fetchable. "standard" and "thorough" also return contradictions[] flagging findings that disagree. Large records are semantically excerpted to the passages relevant to each facet (not head-truncated), so answers deep in a long filing/series aren't missed. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s).
    ConnectorNo auth
  • Patches: drafts a title/metaDescription/canonical/redirect fix for one page's finding. FREE for canonical/redirect (deterministic — canonical is always the page's own URL, redirect always needs an explicit value); title/metaDescription cost one AI-gateway operation UNLESS `value` is given, which sets an explicit replacement instead of drafting one. This is a MUTATION — it creates or overwrites this page+field's draft, but does not publish it (use publish_patch for that). Requires an org admin.
    ConnectorNo auth
  • Search the agent directory of models, MCP servers, frameworks, tools, platforms, work lanes and other resources, filtered by kind, category, capability, tags, free tier or GitHub stars and sorted as you choose. Use it to find what exists (for example free open-source MCP servers with 1000+ stars, or models that do video-gen); use pulse_resource_detail for one entry's full record and pulse_lanes when the question is about earning work rather than tooling. Filters combine with AND; omit all to list everything in the directory. Read-only and idempotent. Works without an API key on the free tier. Returns {count, kinds, resources[]}. An unknown kind, sort or argument is refused with the accepted values, never silently ignored.
    ConnectorNo auth
  • Use this when someone wants popular or trending songs to put on a Reel, TikTok or Story for a business in Malaysia, Singapore, Indonesia, Philippines, Thailand, United States, Canada, United Kingdom, Australia or the UAE, for example 'what songs are trending in Malaysia for Reels?'. Returns this week's songs charting on both Apple Music and Spotify in that country, with the trend (new, up, down) and whether a business account can use them. It is a music-chart signal, not a count of Reels or TikTok uses. Every song is marked business use 'unknown' with the platform's official rule: say so, and never tell a business a song is cleared. Not for picking royalty-free music or for countries outside the list.
    ConnectorNo auth
  • Checks whether a shot plan will cut together before you film or generate it. It looks for crossed lines of action, mismatched eyelines, missing reactions, speakers who are never on screen, missing geography, jump cuts, travel direction, and props that change with no cause. It returns evidence from the plan and fixes it has already tested. The check is instant, and no AI model runs. It checks editing craft, not whether the film is good. Scenes without staging, dialogue or coverage detail come back "not assessed": call shoot_plan_missing_details for the questions to ask your human. Input: plan, a dpl.plan/1 object sent inline (call shoot_plan_format first if you have not written one). Optionally dispositions, the decision log that shoot_plan_record_decision gave you: a finding you decided about earlier, whose evidence has not changed, comes back closed with your reason, and one whose evidence has changed comes back open again (the answer then also says dispositions_applied: how many decisions were applied, reopened or matched no finding). Without dispositions the answer is the same as ever. Output: dpl.findings/1 with stable finding ids, plan_hash, rules_version, any not_assessed scenes and, per finding, its tested fixes (apply one with shoot_plan_apply_fix). A plan that does not validate gets dpl.diagnostics/1 instead: each problem with its path and a fix. We don't keep the plan. We log a one-way fingerprint (hash) of it, its size, the tool, the type of client, the result and the time taken. Needs an agent key from a Shoot Plan account. Free, and it does not count toward the account's 3 free projects a month. Plans up to 8 MB and 120 calls a minute (5,000 a day).
    ConnectorNo auth
  • Set the status of one alert of the isMalicious inbox (an id from list_alerts): ACKNOWLEDGED (seen; still listed by default), RESOLVED (handled; no longer listed by default) or OPEN (new again). Reversible: any status can be set again. A CVE alert (cve.finding) follows its vulnerability finding, for the whole organization: ACKNOWLEDGED acknowledges an open finding, RESOLVED marks a finding not yet closed as patched, OPEN reopens it, and every member's copy of the alert follows; the answer names the finding under `finding`, and the alert's status is the one the API returns (ack_finding sets NOT_AFFECTED or SNOOZED). Scope: the inbox of the user the key belongs to, which for an organization API key is the organization owner's; an alert of another inbox reads as not found. Costs no request of the monthly quota.
    ConnectorNo auth
  • Report whether one finding is fixed, according to yof's latest finished check; it does not run a new check. After a fix, run yof_check first, wait for it to finish, then call this; use yof_findings to get finding ids. Returns finding_id, rule, status, fixed, fixed_at, last_seen, last_check and why; a risk you accepted shows status accepted and fixed false.
    ConnectorNo auth
  • Staff picks in Boston, Denver, San Francisco, Nashville or New York, each with a one-line reason. Use this for “what should I see?”, “what’s good”, “anything worth going to?”, “featured”, “date night”, “romantic”, or any public curated list. Always cite `url` (app deep link /e/?id=). Do not rewrite to /event/. Omit collection to list every public collection (id + title + counts) plus the default featured+popular pages. Intent → collection: date night / romantic / nice night out → date_night (do NOT use sort=popular alone); what’s good / featured → featured; big names / popular → popular; local / underrated → local_scene (or local_bands / under_the_radar); comedy night → comedy (for “comedy this week?” prefer search_shows event_type=comedy); jazz → jazz (or search genre=jazz); kids / family → tots_picks; older crowd / boomer → senior; foobos / Scott / Tot staff → foobos / scotts_picks / tots_picks; free curated → free_tonight (or shows_free); punk curated → punk (or search genre=punk); weeknight gems → weeknight_gems; St. Patrick’s → st_patricks. Not personalized For You — there is no account on this API. Each pick includes editorial `why` when the curated row has one so you can cite the reason. Each collection is paginated (default 20, max 50) and includes its own total.
    ConnectorNo auth
  • SeekSat's ten popular satellites (ISS, Tiangong, Hubble, weather satellites and a few others): always all ten, in a fixed order, with aliases, page url and orbit data freshness. Not the full list: every other tool accepts any NORAD catalog number. To find another satellite by name use search_satellites; for one satellite's facts and TLE use get_satellite. Takes no input, reads only SeekSat's own catalog and does not fail. Read-only, free, no key needed; up to 120 requests per 60 seconds per IP address.
    ConnectorNo auth
  • Show exactly what Komuta would change to fix ONE current Service Doctor finding, without changing anything: a readiness probe on the service's own port (Configuration.ReadinessProbeMissing), a higher autoscaling maximum (Configuration.AutoscalingAtCeiling) or the cheaper package Doktor suggests (Cost.RightsizePackage). Returns the changes, the monthly cost delta (costDeltaIsCeiling true means at most, only while the extra replicas run; negative means savings) and an approvalDigest bound to this exact change. Refused when one-click fixes are off, the service is on the free plan, the caller cannot edit the service, or the finding is not current or has no safe fix. Returns: { findingCode, kind, changes: [{ setting, before, after }], monthlyCostDelta, costDeltaIsCeiling, approvalDigest }. Show user: every change as setting: before → after, and the monthly cost delta in plain words, then ask whether to apply it. Never show user: approvalDigest and other internal identifiers; keep the digest only for komuta_apply_service_doctor_fix. Sends: the service id and the finding code only.
    ConnectorOAuth
  • Check whether a change the user made THEMSELVES (not a one-click fix; for example after a Doktor AI fix draft) resolved one Service Doctor finding. Call only when the user explicitly asks to check a change they made: every call runs Service Doctor and records the result. Pass the finding code exactly as Service Doctor returned it and changedAtUtc, the UTC time the user started the change: within the last 7 days and not in the future. Ask the user when they made the change if they did not say; never invent it. Komuta waits for a successful deploy that started after changedAtUtc, then checks the finding and user impact (errors and p95 latency in the traffic after that deploy, compared with the 24 hours before the change when that had enough traffic). verification.configuration is always NotApplicable because Komuta did not make the change. summaryCode: Verified only when the deploy, the finding and user impact all pass; AwaitingDeployment (no deploy finished after the change yet); DeploymentFailed (the deploy after the change failed or is unhealthy); RiskStillPresent; RiskClosedImpactUnproven (finding gone but too little traffic, say plainly this is not a verification); ImpactRegressed; ObservingImpact (tell the user impactReadyAtUtc instead of suggesting to retry soon); RiskUnassessed (Komuta cannot prove from its recent decisions that this finding was present, for example cost findings, findings below Watch, or older ones; do not call it fixed). Returns: { findingCode, verification: { configuration, deployment, risk, impact, summaryCode, requestCount, minimumRequestCount, errorRatePercent, baselineErrorRatePercent, p95LatencyMs, baselineP95LatencyMs, observedFromUtc, observedToUtc, impactReadyAtUtc } }. Show user: what was confirmed and what was not, facet by facet, in plain words, and the change time you used; never call anything but Verified verified. Never show user: serviceId and other internal identifiers. Sends: the service id, the finding code and the change time; the backend runs Service Doctor and enforces access.
    ConnectorOAuth