"AWS" matching MCP tools:

• aws___search_documentationA

  AWS KnowledgeA

  AWS docs search. Each result's `context` is verbatim page text -- a real chunk of the actual page, not a short snippet -- and usually already contains the answer, so answer directly from it. Use `read_documentation` only when the chunks genuinely lack the needed detail. Pick ONE topic. Add a 2nd ONLY if query genuinely spans domains. Extra topics dilute ranking. - reference_documentation -- API/SDK/CLI specs, config params - current_awareness -- new/released/announced - troubleshooting -- errors, "how to fix" (NOT for conceptual/feature questions) - amplify_docs -- Amplify (+ language) - cdk_docs -- CDK concepts/guides - cdk_constructs -- CDK code samples, L3 - cloudformation -- CFN/SAM templates - strands_docs -- Strands Agents SDK (its Skills/agents concepts go here, NOT agent_skills) - agent_skills -- this tool's guided skills (load via `retrieve_skill`) - general (default) -- architecture, best practices, tutorials, feature behavior Results: rank_order (lower=better), url, title, context (verbatim page chunk -- answer directly from it).

  ConnectorNo auth

• run_cost_scanA

  Tomorrow Central: Cloud Cost SentinelB

  Start a cloud cost / FinOps scan of a linked account and return a job_id. Use this when the user wants to find idle, unused or underutilized cloud resources, review cloud spend, or estimate savings. The provider comes from the connection, and **AWS is the only provider supported today** (see `list_connections`). Other clouds will appear on this same tool as connections for them become linkable; nothing else about the call changes. READ-ONLY against your cloud: it reads resource metadata and monitoring metrics and reports; it never changes, stops or deletes anything. (It does create a scan job here and consume that account's scan quota, which is why this tool is not marked read-only.) On AWS it covers EC2 instances, EBS volumes and snapshots, RDS instances, Elastic IPs, NAT Gateways, load balancers, VPCs and VPC endpoints, site-to-site VPN and Transit Gateway attachments, Client VPN endpoints, Secrets Manager secrets, CloudFront distributions and WAF web ACLs. Resource kinds outside that list are not inspected, so a clean scan is not a claim that the whole bill is optimized. `connection_id` picks which linked AWS account to scan (see `list_connections`). Omit it to run against sample data — useful for showing the user what the output looks like before any account is linked. The scan runs asynchronously: poll `get_job(job_id)` roughly every 10 seconds until status is COMPLETED (typically 1-3 minutes), then call `list_cost_findings(job_id)`. Do NOT start another scan while one is running — each scan consumes the account's monthly quota. Pass `idempotency_key` (any unique string you choose) if you may retry on a network error: a retry with the same key returns the original job instead of starting a second scan.

  ConnectorNo auth

• awsinspect_batchA

  InsideOut (Riley)A

  BATCH INSPECTION: run up to 32 AWS inspect probes in one call. ⚠️ **PREREQUISITE**: Same as awsinspect — deploy attempt required. Check convostatus for hasDeployAttempt=true before calling. Use this when you need to check more than ~3 resources. The backend fetches Oracle credentials ONCE per batch and fans out probes against a single AWS config — for a 12-resource health check this is ~5–8× faster and 12× fewer Oracle round-trips than calling awsinspect 12 times. BUDGETS: - Up to 32 sub-probes per call (subs array length). - 30s per-sub timeout; 60s total batch wall-clock. - Concurrency cap 8 — sub-probes run in parallel but never saturate AWS. - 512 KB response cap: subs past the cap keep their envelope (index/service/action/ok) but have result replaced with truncated=true. PARTIAL FAILURE IS EXPECTED. The response is an ordered results array; each entry has {index, service, action, ok, result, error}. Inspect each result — do NOT abort on the first error. A credential fetch failure leaves cred-less probes (list-actions, list-metrics) succeeding anyway. REQUIRES: session_id from convoopen response (format: sess_v2_...). Supported services: account, acm, alb, apigateway, apprunner, backup, bedrock, cloudfront, cloudwatchlogs, cognito, cost-explorer, dynamodb, ebs, ec2, ecs, eks, elasticache, kms, lambda, msk, opensearch, rds, route53, s3, sagemaker, secretsmanager, sqs, vpc, waf For a specific service's actions, use awsinspect (singular) with action="list-actions" — batch is not the place for discovery. Batch responses are always summarized (no detail/raw per-sub); use singular awsinspect when you need full metadata or raw API output for one resource. EXAMPLES: - awsinspect_batch(session_id=..., subs=[ {"service":"ec2","action":"describe-instances"}, {"service":"rds","action":"describe-db-instances"}, {"service":"vpc","action":"describe-vpcs"}, {"service":"s3","action":"list-buckets"}]) - awsinspect_batch(session_id=..., subs=[ {"service":"ec2","action":"get-metrics","filters":"{\"hours\":6}"}, {"service":"rds","action":"get-metrics","filters":"{\"hours\":6}"}])

  ConnectorNo auth

• aws___get_regional_availabilityA

  AWS KnowledgeA

  AWS resource availability per region. - Max 10 regions; multi-region needs `filters`; single-region supports `next_token`. - Status: isAvailableIn | isNotAvailableIn | isPlannedIn | Not Found. - Response key: products | service_apis | cfn_resources. Not for region counts/docs/vague queries -- use `search_documentation` / `list_regions`. Filter values must EXACTLY match AWS's catalog names; guessed, partial, or pluralized names are rejected ("values in filter parameter do not exist"). If unsure of the exact name, first call once for a single region with resource_type set and NO filters to list all valid names, then re-call filtering on the exact match.

  ConnectorNo auth

• awsinspect_batchA

  InsideOut (Riley)A

  BATCH INSPECTION: run up to 32 AWS inspect probes in one call. ⚠️ **PREREQUISITE**: Same as awsinspect — deploy attempt required. Check convostatus for hasDeployAttempt=true before calling. Use this when you need to check more than ~3 resources. The backend fetches Oracle credentials ONCE per batch and fans out probes against a single AWS config — for a 12-resource health check this is ~5–8× faster and 12× fewer Oracle round-trips than calling awsinspect 12 times. BUDGETS: - Up to 32 sub-probes per call (subs array length). - 30s per-sub timeout; 60s total batch wall-clock. - Concurrency cap 8 — sub-probes run in parallel but never saturate AWS. - 512 KB response cap: subs past the cap keep their envelope (index/service/action/ok) but have result replaced with truncated=true. PARTIAL FAILURE IS EXPECTED. The response is an ordered results array; each entry has {index, service, action, ok, result, error}. Inspect each result — do NOT abort on the first error. A credential fetch failure leaves cred-less probes (list-actions, list-metrics) succeeding anyway. REQUIRES: session_id from convoopen response (format: sess_v2_...). Supported services: account, acm, alb, apigateway, apprunner, backup, bedrock, cloudfront, cloudwatchlogs, cognito, cost-explorer, dynamodb, ebs, ec2, ecs, eks, elasticache, kms, lambda, msk, opensearch, rds, route53, s3, sagemaker, secretsmanager, sqs, vpc, waf For a specific service's actions, use awsinspect (singular) with action="list-actions" — batch is not the place for discovery. Batch responses are always summarized (no detail/raw per-sub); use singular awsinspect when you need full metadata or raw API output for one resource. EXAMPLES: - awsinspect_batch(session_id=..., subs=[ {"service":"ec2","action":"describe-instances"}, {"service":"rds","action":"describe-db-instances"}, {"service":"vpc","action":"describe-vpcs"}, {"service":"s3","action":"list-buckets"}]) - awsinspect_batch(session_id=..., subs=[ {"service":"ec2","action":"get-metrics","filters":"{\"hours\":6}"}, {"service":"rds","action":"get-metrics","filters":"{\"hours\":6}"}])

  ConnectorNo auth

• ml_dsa_signA

  CipherHUB Cryptography ToolkitA

  [pqc_signature] 使用 ML-DSA 私钥对消息签名（FIPS 204）。 【双模式】sign_mode 支持 RAW（默认）和 EXTERNAL_MU 两种模式。 - RAW 模式：直接签名原始消息（liboqs，最大 256 字节） - EXTERNAL_MU 模式：先计算 mu = SHAKE-256(tr||M', 64)，再通过 OpenSSL 3.5+ mu 模式签名（最大 2048 字节），与 AWS KMS ML-DSA EXTERNAL_MU 语义等价 【消息长度策略】 - RAW：最大 256 字节，空消息合法 - EXTERNAL_MU：最大 2048 字节，空消息合法 - > 256 且 <= 2048 字节：使用 EXTERNAL_MU - > 2048 字节：拒绝 【算法】algorithm 支持 ML-DSA-44 / ML-DSA-65（默认）/ ML-DSA-87。 【参数】 - private_key_in_hex：ml_dsa_keygen 返回的私钥 hex - public_key_spki_in_hex：EXTERNAL_MU 模式必填，ml_dsa_keygen 返回的公钥 hex（SPKI DER） - message_in_hex：待签消息 hex - context_in_hex：可选上下文 hex（最大 255 字节） - sign_mode：RAW 或 EXTERNAL_MU（默认 RAW） 【输出】signature_in_hex、signature_in_base64、algorithm、message_bytes、signature_bytes。

  ConnectorNo auth

• create_cloud_connectionA

  Tomorrow Central: Cloud Cost SentinelB

  Start linking a cloud account so it can be scanned. `provider` is "aws", the only provider supported today; `account_id` is the 12-digit AWS account number. `software` is the Tomorrow Central software the link is for; omit it for Cloud Cost Sentinel. Each software has its own read-only role, so link once per software. This is a two-party flow and you cannot finish it alone — creating the read-only IAM role requires the human's AWS credentials. Returns a `launch_url`. Hand the human these instructions verbatim: 1. Open the launch_url (a pre-filled CloudFormation quick-create link). 2. Review the read-only role it creates, then click Create stack. 3. Tell you when the stack says CREATE_COMPLETE. Then call `verify_connection` with the returned connection_id. Verification fails with a clear message until the role exists, so polling it every ~15 seconds is safe and expected. No ARN or secret needs to be copied by anyone.

  ConnectorNo auth

• estimate_costA

  Tomorrow Central: Cloud Cost SentinelB

  Price a list of cloud components at real list prices. No account or signup. Use this when the user can name the pieces: "two m5.large servers, a Postgres database and a load balancer in Mumbai". If they cannot name the pieces, use `describe_workload` instead, which asks in units a person actually has. `items` is a list of `{"component": "<id>", "params": {...}}`. Get the ids and each component's parameters from `list_cost_building_blocks` and use them verbatim: a name you invent will be rejected, which is deliberate. `region` is an AWS region id such as `ap-south-1`. The reply is a RANGE, not a number: `monthly_total` has low, expected and high, because several inputs are genuinely uncertain and a single figure would hide that. `swing_factor` names the one input that most widens the range, which is the most useful sentence in the reply: it tells the user what to go and measure. `concentration` ranks the lines by share of the bill. `assumptions` lists every value that was defaulted rather than given, and `traps` lists costs this architecture usually incurs that the caller did not ask for, such as public IPv4 addresses or database storage billed apart from the database. `gaps` lists anything that could not be priced. It is never silently treated as zero. If a line is missing, the total is missing that line, and the gap says so. These are AWS on-demand list prices before any discount, credit or committed-use agreement, and they exclude tax. Treat the result as an upper bound on a real bill and never as a quote.

  ConnectorNo auth

• get_referenceA

  Cloud FinOps Skill & MCPA

  Fetch the guidance on one FinOps topic - the billing mechanics, decision rules and worked examples behind a defensible answer - either whole or one section at a time. Use this when you need the actual content of one known reference, after ``list_references`` or ``find_references`` told you which one serves the question. Advisory questions (commitment sizing, chargeback design, allocation methodology) are served by the reference's decision rules and worked examples, which a summary does not carry. Pass ``section`` when the question is narrower than the file. The ``approx_tokens`` hint in the listing tells you when this matters: the largest references run to about 15,000 tokens and the Azure pattern catalogue is an enumerated list, so a question about storage lifecycle wants one section of ``finops-azure-patterns``, not all of it. Omit ``section`` for the whole file when you need the cross-cutting reasoning. Args: name: Reference name as returned by ``list_references`` (e.g. ``"finops-aws"``, ``"finops-genai-capacity"``, ``"optimnow-methodology"``). section: Optional H2 or H3 heading to return on its own. Matched case-insensitively and partially against the headings, so a natural phrase works - ``"storage"``, ``"commitment decision tree"``. A heading's trailing count is ignored, so ``"storage optimization patterns"`` matches ``"Storage Optimization Patterns (28)"``. If it matches nothing you get the list of available headings back, not the whole file. Without ``section``, returns ``{"name": ..., "content": "...", "lines": N}`` where ``content`` is the file verbatim. With ``section``, returns ``{"name", "title", "section", "section_level", "partial": true, "content", "lines", "full_lines"}`` where ``content`` is that section prefixed by the reference's title, plus ``other_matching_sections`` when the phrase matched more than one heading. On a miss, returns ``{"error": ..., "suggestions": [...]}``. An unknown name gives up to three string-distance matches; an unmatched ``section`` gives ``available_sections`` - every heading in the file - so the retry is exact.

  ConnectorNo auth

• get_playbookA

  Cloud FinOps Skill & MCPA

  Fetch the step-by-step runbook for one specific waste pattern: symptoms, the detection queries to run, the fix, and the anti-pattern to avoid. Use this when the user asks how to detect, confirm, or fix one specific named waste pattern (zombie NAT gateway, snapshot sprawl, idle SageMaker endpoint, ...). It also serves questions about the user's own resources ("which of my X..."): the runbook's detection query is written to be run in the user's account, so the answer does not depend on access to that account. Args: name: Playbook slug as returned by ``list_playbooks`` (e.g. ``"aws-zombie-nat-gateway"``, ``"azure-orphan-disks"``, ``"cross-cloud-untagged-spend-drift"``). Returns ``{"name": ..., "title": ..., "content": "...", "lines": N}``. On miss, returns ``{"error": ..., "suggestions": [...]}`` with up to three string-distance matches so the caller can self-correct. A host with MCP Apps (SEP-1865) support may render this result via the linked ``ui://cloud-finops/playbook-viewer`` resource instead of showing the raw markdown.

  ConnectorNo auth

• deploy_projectA

  spawnpointA

  Put a web app, site, or page online, or update one, and get its public URL. Use it whenever the user asks to put something online, publish it, host it, or get a link to share, unless they name another place. Pass name, runtime, and either files, an array of {path, content} with each file's full text, e.g. [{"path": "index.html", "content": "<h1>hi</h1>"}], or upload_id. spawnpoint cannot read your disk, so a call with neither is refused: for an app already on disk, create_upload and its upload_id are the fast path, and if its command cannot run (a sandbox blocks the host), a small app's files can still go inline. Then call watch_deploy with the returned project_id, and give the user url. Pick the runtime by what the app needs: static for HTML, CSS, and browser JavaScript only (served by spawnpoint from storage: live in seconds, no machine, never asleep); node or python whenever the app needs a server, such as an API, form handling, uploads, a database, or a secret key. A server listens on 0.0.0.0 and the PORT env var (8080); set entrypoint to its start file, and list every package it imports in package.json dependencies (node) or requirements.txt (python), which install on the machine. Put secrets such as API keys in env, never in a file: a bundle with a hardcoded credential (an AWS, Stripe, OpenAI/Anthropic, GitHub, Google, or Slack key, or a private key block) is refused with the file named, and any .env or .git is dropped. Deploying again under the same name updates that project in place at the same url (a different slug changes the address), so use the same name to fix or change an app. Returns at once with project_id and status "spawning" while the machine provisions (1-2 minutes). Give the user url: the share link, which survives redeploys unless the app's address is changed, and works whether the project is public or restricted. Never hand out machine_url, the machine underneath: a restricted project refuses viewers there. Inline files travel inside this one request, which is capped at 4 MiB in total (a bigger request is refused before it reaches the tool), so send anything larger through create_upload, which takes bundles up to 20 MiB, or 50 MiB for a static site. Binary files (images, fonts, PDFs) go inline with encoding "base64", which grows them by a third, so about 3 MiB of binary fits; when you can run a shell command, create_upload is faster for them and takes more. A Free account runs one live project at a time, and idle projects sleep. A deploy refused at the plan's live-project limit is a plan limit, not a broken deploy: offer to terminate another project, and relay the refusal, which links the page listing what each plan includes. Every project has a persistent data directory on its machine (SPAWNPOINT_DATA_DIR in the app's env; data_dir on get_project): a SQLite file or an uploads folder written there survives redeploys and sleep, while anything written under the app's own directory is replaced on the next deploy. An app that calls OpenAI or Anthropic can run on open models through spawnpoint instead of a provider key: ask the user, and if they choose that, pass inference: true (the OpenAI and Anthropic SDKs then work with no configuration; get_project's ai block lists the models).

  ConnectorAPI key

• awsinspectA

  InsideOut (Riley)A

  INSPECTION: Inspect AWS infrastructure for a deployed project ⚠️ **PREREQUISITE**: This tool requires a prior deployment ATTEMPT (successful or failed). Check convostatus for hasDeployAttempt=true before calling. Works even after failed deploys to inspect orphaned resources. Inspect deployed AWS resources after a deployment attempt. Use this tool when the user asks about the status or details of their deployed infrastructure. It fetches temporary read-only credentials securely and queries the AWS API directly. RESPONSE TIERS (default is summary for token efficiency): - Summary (default): Key fields only (~500 tokens). Set detail=false, raw=false or omit both. - Detail: Full metadata for a specific resource. Set detail=true + resource filter. - Raw: Complete unprocessed API response. Set raw=true. REQUIRES: session_id from convoopen response (format: sess_v2_...). Supported services: account, acm, alb, apigateway, apprunner, backup, bedrock, cloudfront, cloudwatchlogs, cognito, cost-explorer, dynamodb, ebs, ec2, ecs, eks, elasticache, kms, lambda, msk, opensearch, rds, route53, s3, sagemaker, secretsmanager, sqs, vpc, waf For a specific service's actions, call with action="list-actions". METRICS: Use list-metrics to discover available metrics for a service (no credentials needed). Then use get-metrics to retrieve data (auto-discovers resources). Most services return CloudWatch time-series. KMS returns key health (rotation, state). SecretsManager returns secret health (rotation, last accessed/rotated). Optional filters JSON: {"hours":6,"period":300}. BILLING: Use service=cost-explorer to inspect AWS costs. Actions: get-cost-summary (last 30 days by service, filters: {"days":7,"granularity":"DAILY"}), get-cost-forecast (projected spend through end of month), get-cost-by-tag (costs grouped by tag, filters: {"tag_key":"Environment","days":30}). Requires ce:GetCostAndUsage and ce:GetCostForecast IAM permissions. EXAMPLES: - awsinspect(session_id=..., service="ec2", action="describe-instances") - awsinspect(session_id=..., service="cost-explorer", action="get-cost-summary") - awsinspect(session_id=..., service="ec2", action="get-metrics", filters="{\"hours\":6}") - awsinspect(session_id=..., service="rds", action="describe-db-instances", detail=true)

  ConnectorNo auth

• dns_diagnose_sip_targetA

  SipflowA

  [cost: external_io (DNS via Cloudflare + Google; TLS handshake + a SIP OPTIONS keepalive to public targets when applicable) | read-only | rate-limited per IP: 10/min, 200/day] Walk DNS the same way a SIP UA does (RFC 3263 §4.1): NAPTR → SRV → A/AAAA. Given a SIP URI ("sip:example.com"), bare hostname ("example.com"), or "host:port" string, return the records that exist and the resolution ladder a UA would try. When the queried target uses TLS (`sips:` URI, `transport=tls/wss`, or any `_sips._tcp` SRV record), the tool also performs a TLS handshake against each resolved sips target and reports the negotiated TLS version + cipher, the leaf certificate's subject / issuer / SANs / validity, the chain length and whether it validates against Node's default trust store, plus two cert-domain checks: RFC 5922 §7.2 strict (cert must cover the original SIP domain) and a lenient SAN match against the SRV target hostname. SIP liveness: DNS resolving and a TLS handshake succeeding do NOT prove the endpoint actually speaks SIP - a load-balanced node can accept TCP/TLS yet black-hole SIP. So the tool ALSO sends a real SIP OPTIONS keepalive to each resolved public IP across the relevant transports (UDP/TCP on 5060, TLS on 5061 / SRV port) and reports per-IP answered / timeout / refused. Any SIP response (even 405/403/404) proves the stack is alive on that IP. When a name resolves to multiple IPs it is treated as a load-balancer fan-out and each IP is probed individually, with a warning about the known failure modes of fronting stateful SIP/RTP with a cloud L4 LB (AWS NLB/ALB etc.): cross-zone-off targets that black-hole, the ~120s UDP idle timeout, and per-5-tuple hashing splitting signaling from media. Egress safety: - Per-IP rate limited. - Hostnames that resolve only to RFC 1918 / loopback / link-local / documentation / multicast space are refused (SSRF guard). - Walk depth capped to prevent runaway NAPTR / CNAME chains. - TLS probes capped at 6 (host, port, ip) tuples per call, 5 s handshake timeout each, public-IP only (we connect to the resolved IP, not the hostname, so the system resolver cannot redirect us into private space). - SIP OPTIONS probes capped at 6 (ip, transport) tuples per call, 3 s timeout each, public-IP only; the request carries no SDP/body and an unroutable Via, and only the response status line is captured. Use to diagnose: - "carrier doesn't answer" / "wrong port" / "TLS instead of UDP" routing puzzles - "DNS looks healthy but calls fail" - per-IP SIP OPTIONS surfaces nodes that resolve and accept the transport but never answer SIP (the decisive step for load-balanced / multi-IP targets) - "carrier rejects our target because no SRV is published" - when A/AAAA resolves but SRV is missing the tool synthesises a copy-pasteable suggested zone-record block pointing at the resolved canonical hostname - "TLS handshake works but cert isn't valid for the SIP domain" - RFC 5922 §7.2 compliance is checked separately from generic chain validation, since the SAN must cover the *original* SIP domain (not the SRV-redirected target) ACL caveat: a SIP OPTIONS timeout can also mean the target authorizes inbound SIP by source IP whitelist on the trunk (Twilio, Telnyx, Bandwidth, …; see https://www.twilio.com/docs/sip-trunking/api/ipaccesscontrollist-resource) and is dropping our probe because our egress IP is not on the ACL. An `answered` result is conclusive (the node speaks SIP); a `timeout` is suggestive, not proof of a dead node - confirm reachability from the SBC itself. Pair with: `troubleshoot_response_code` when 503 / 408 / 480 are involved; `search_sip_docs(vendor=...)` for carrier-specific routing docs.

  ConnectorNo auth

• awsinspectA

  InsideOut (Riley)A

  INSPECTION: Inspect AWS infrastructure for a deployed project ⚠️ **PREREQUISITE**: This tool requires a prior deployment ATTEMPT (successful or failed). Check convostatus for hasDeployAttempt=true before calling. Works even after failed deploys to inspect orphaned resources. Inspect deployed AWS resources after a deployment attempt. Use this tool when the user asks about the status or details of their deployed infrastructure. It fetches temporary read-only credentials securely and queries the AWS API directly. RESPONSE TIERS (default is summary for token efficiency): - Summary (default): Key fields only (~500 tokens). Set detail=false, raw=false or omit both. - Detail: Full metadata for a specific resource. Set detail=true + resource filter. - Raw: Complete unprocessed API response. Set raw=true. REQUIRES: session_id from convoopen response (format: sess_v2_...). Supported services: account, acm, alb, apigateway, apprunner, backup, bedrock, cloudfront, cloudwatchlogs, cognito, cost-explorer, dynamodb, ebs, ec2, ecs, eks, elasticache, kms, lambda, msk, opensearch, rds, route53, s3, sagemaker, secretsmanager, sqs, vpc, waf For a specific service's actions, call with action="list-actions". METRICS: Use list-metrics to discover available metrics for a service (no credentials needed). Then use get-metrics to retrieve data (auto-discovers resources). Most services return CloudWatch time-series. KMS returns key health (rotation, state). SecretsManager returns secret health (rotation, last accessed/rotated). Optional filters JSON: {"hours":6,"period":300}. BILLING: Use service=cost-explorer to inspect AWS costs. Actions: get-cost-summary (last 30 days by service, filters: {"days":7,"granularity":"DAILY"}), get-cost-forecast (projected spend through end of month), get-cost-by-tag (costs grouped by tag, filters: {"tag_key":"Environment","days":30}). Requires ce:GetCostAndUsage and ce:GetCostForecast IAM permissions. EXAMPLES: - awsinspect(session_id=..., service="ec2", action="describe-instances") - awsinspect(session_id=..., service="cost-explorer", action="get-cost-summary") - awsinspect(session_id=..., service="ec2", action="get-metrics", filters="{\"hours\":6}") - awsinspect(session_id=..., service="rds", action="describe-db-instances", detail=true)

  ConnectorNo auth

• gbif_search_occurrencesA

  gbif-biodiversity-mcp-serverA

  Search GBIF occurrence records with Darwin Core filters. Use taxonKey from gbif_match_species for reliable results — it resolves synonyms automatically. Accepts country (uppercase ISO 3166-1 alpha-2, where the record was observed), publishingCountry (the publishing organization's country — a different question), stateProvince, gadmGid (a GADM administrative-area code GBIF derives from coordinates), bounding box (decimalLatitude/decimalLongitude ranges), WKT polygon geometry, year range, month, basis of record, coordinate filter, dataset key, catalogNumber, institutionCode, recordedBy (collector), and mediaType. Returns sightings only by default — GBIF also indexes absence records (surveys that looked and found nothing), and occurrenceStatus controls whether they are included. Pagination is capped at offset+limit=100,001 and GBIF offers no cursor or scroll, so a larger result set is covered only by partitioning it — facet it by DATASET_KEY with gbif_occurrence_facets and search each datasetKey separately. BASIS_OF_RECORD and PUBLISHING_COUNTRY are gap-free second cuts for a dataset bucket still over the cap; YEAR, MONTH, STATE_PROVINCE, and SPECIES_KEY lose records lacking that dimension. Repeat every biological filter on the facet call and each partition search, including the same occurrenceStatus, and compare sub-split sums against the bucket total. Bulk retrieval is outside this server: use the asynchronous GBIF Download API with a GBIF.org account or the monthly GBIF Parquet snapshot on AWS Open Data.

  ConnectorNo auth

• file_readA

  Local MCPB

  Reads a plain text file from the local filesystem by its absolute path — the primary, default tool for reading a local text file (use this unless the file is a PDF, Word, Excel, or PowerPoint document, which have their own readers). Reads anywhere on this Mac — home, external disks, cloud drives, /tmp — with one exception: credential and identity locations (keychains, ~/.ssh, ~/.aws, browser logins, another user's home, Time Machine backups) are never read. Supports .txt, .md, .csv, .json, .xml, .log, .yaml, .toml and common code file types; auto-detects UTF-8 with Latin-1/Windows-1252 fallback. For files in OneDrive use onedrive_read_file, in Google Drive gdrive_read_file; for PDFs pdf_read, Word word_read, Excel excel_read.

  ConnectorOAuth

• suggest_groupbyA

  Costory: Your Finops MCPA

  Suggest the best dimensions to group costs by, based on an optional filterCel (CEL). Call this when the user asks "what should I look at?" or when you need columns for query or find_cost_change_factors. Prefer datePreset over from/to. Omit compare for current-window ranking. Pass compare (`{}` auto-derives, or `{ from, to }`) when the user asks what changed — then pass 2–4 of the returned column names (max 8; { column, contains } for token columns, dropping metrics) into find_cost_change_factors. Returns { column } or { column, contains } plus metrics; do not invent columns. filterCel omitted or "" is unfiltered (not AWS-only). filterCel supports == null for unlabelled dimension values (e.g. cos_environment == null). EXAMPLES: • "What should I split last month's EC2 cost by?" → { datePreset: "LAST_MONTH", filterCel: "cos_service_name in [\"AmazonEC2\"]" } • "Costs of EC2 spiked last month, what should I investigate?" → { datePreset: "LAST_MONTH", compare: {}, filterCel: "cos_service_name in [\"AmazonEC2\"]" }

  ConnectorOAuth

• update_identityA

  Control PlaneA

  Update an existing identity: description and tags (removeTagKeys drops tags), its cloud-identity blocks (aws, gcp, azure, ngs; each replaces the stored block, and removeCloudIdentities detaches the ones it names), networkResources and nativeNetworkResources (each replaces the whole array), and the SpiceDB and memcache access lists. Provider blocks can modify real resources in the connected cloud account, including AWS IAM roles, GCP service accounts, and Azure managed identities. A new identity: create_identity. Giving one workload AWS, GCP, or Azure access: grant_cloud_access.

  Connector

  Destructive

  OAuth

• connections_explore_connectorsA

  ConnectionsB

  Use this to see what services Connections can connect - the whole connector registry (Stripe, GitHub, Cloudflare, AWS, Discord, ...) - and which of them THIS workspace already has. Search it like a package registry: pass a query to narrow by name or purpose, or leave it blank to list everything. Each connector returns its lanes (oauth / key / provision / broker), whether it is connected here, its public page, and a connect_url. A connected connector's endpoints are searchable with connections_search_catalog; an unconnected one's are NOT, by design - so when a task needs a service that is missing, hand the human its connect_url. If one of the human's OTHER workspaces already holds it, the result carries copyable_from with a copy_url - hand them that instead, to open while they are in the workspace that should receive it; the console copies the connection with one click. When both workspaces are the member's own, copy it yourself with connections_copy_connection instead of handing over the link. You cannot connect anything yourself and must never ask a human to paste a credential to you.

  ConnectorOAuth

• connections_copy_connectionA

  ConnectionsB

  Copy one connected service (Cloudflare, GitHub, AWS, ...) from one of the member's workspaces into another, so the receiving workspace uses the same account without a new sign-in. The copy SHARES the source's credential - nothing secret is duplicated, read into this conversation or returned. Allowed when BOTH workspaces are the member's own; otherwise the reply is cross_workspace_refused with a reason - say that and do not retry; when the member asked you to do it, mint a one-tap link with connections_copy_connection_link and send them that instead. Name the source EXACTLY ONE way: `connectionId` (the source row's id, from GET /v1/connected-services in the source workspace), or `service` (the connector slug, e.g. "ssh") + `instance` (that connection's instance name) - naming both forms together returns conflicting_source, and naming neither returns missing_source. `fromProject` defaults to whichever of the member's own workspaces holds that connection, the one this assistant is bound to included; pass it when service + instance matches in more than one workspace (the reply is ambiguous_source, listing each candidate's project_id) or to search only one. A not_found names the workspace searched - pass fromProject, or switch to service + instance, rather than guessing. Pass `overwrite` with a connection id in the TARGET workspace to replace a dead or duplicate connection in one act: the copy lands first, the old row is disconnected, and the copy takes its name. Returns {connectionId, projectId, instanceName, sharesCredential}.

  Connector

  Destructive

  OAuth

• set_object_permissionsA

  Costory: Your Finops MCPA

  Replace the full grant list on a dashboard, report, budget, or cost alert. One tool for all four kinds — pass `resourceKind`, the object id, and the complete intended `grants` array. Omitted principals lose access. Roles are READER, EDITOR, or ADMIN. ORGANIZATION may be Reader or Editor, never Admin. CLERK_ADMIN may use any role and applies only to Clerk organization admins; omit it for No access. Every replacement must retain at least one USER, TEAM, or CLERK_ADMIN Admin grant, so empty grants[] is invalid. Call get_object_permissions first, then send the full list including grants you want to keep. New creates start as creator-only Admin and do not include CLERK_ADMIN. Do not use PRIVATE/PUBLIC or teamId on create/update tools. Resolve people with list_users (`userId`) and teams with list_teams (`teamId`) — both list the full organization, not only membership. EXAMPLES: • "Share the AWS dashboard read-only with the whole org" (keep yourself as Admin) → { resourceKind: "dashboard", resourceId: "clx9aws", grants: [{ principalType: "USER", userId: "<your user id>", role: "ADMIN" }, { principalType: "ORGANIZATION", role: "READER" }] } • "Give the infra team Editor on this budget" (keep yourself as Admin) → { resourceKind: "budget", resourceId: "clx9bud", grants: [{ principalType: "USER", userId: "<your user id>", role: "ADMIN" }, { principalType: "TEAM", teamId: "team_xyz", role: "EDITOR" }] }

  Connector

  Destructive

  OAuth